CN113558602B - Hypothesis-driven cognitive impairment brain network analysis method - Google Patents
Hypothesis-driven cognitive impairment brain network analysis method Download PDFInfo
- Publication number
- CN113558602B CN113558602B CN202110653150.2A CN202110653150A CN113558602B CN 113558602 B CN113558602 B CN 113558602B CN 202110653150 A CN202110653150 A CN 202110653150A CN 113558602 B CN113558602 B CN 113558602B
- Authority
- CN
- China
- Prior art keywords
- brain
- brain network
- cognitive impairment
- network
- hypothesis
- 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.)
- Active
Links
- 210000004556 brain Anatomy 0.000 title claims abstract description 132
- 208000010877 cognitive disease Diseases 0.000 title claims abstract description 42
- 238000000034 method Methods 0.000 title claims abstract description 23
- 208000028698 Cognitive impairment Diseases 0.000 title claims abstract description 18
- 238000003012 network analysis Methods 0.000 title claims abstract description 9
- 238000005259 measurement Methods 0.000 claims abstract description 20
- 239000011159 matrix material Substances 0.000 claims abstract description 19
- 230000000750 progressive effect Effects 0.000 claims abstract description 14
- 238000010801 machine learning Methods 0.000 claims abstract description 13
- 208000027061 mild cognitive impairment Diseases 0.000 claims abstract description 13
- 238000012360 testing method Methods 0.000 claims abstract description 9
- 208000024827 Alzheimer disease Diseases 0.000 claims abstract description 8
- 238000007781 pre-processing Methods 0.000 claims abstract description 8
- 238000004458 analytical method Methods 0.000 claims abstract description 7
- 238000010276 construction Methods 0.000 claims abstract description 4
- 238000012795 verification Methods 0.000 claims abstract description 4
- 238000012216 screening Methods 0.000 claims description 9
- 230000008859 change Effects 0.000 claims description 7
- 238000000528 statistical test Methods 0.000 claims description 7
- 230000002776 aggregation Effects 0.000 claims description 6
- 238000004220 aggregation Methods 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 6
- 238000003384 imaging method Methods 0.000 claims description 6
- 239000013598 vector Substances 0.000 claims description 6
- 230000001747 exhibiting effect Effects 0.000 claims description 4
- 238000005192 partition Methods 0.000 claims description 4
- 238000012706 support-vector machine Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000000638 solvent extraction Methods 0.000 claims description 3
- 238000010219 correlation analysis Methods 0.000 claims description 2
- 230000011218 segmentation Effects 0.000 claims description 2
- 238000012545 processing Methods 0.000 claims 1
- 201000004569 Blindness Diseases 0.000 abstract description 4
- 238000005457 optimization Methods 0.000 abstract description 4
- 230000008569 process Effects 0.000 abstract description 4
- 230000036541 health Effects 0.000 abstract description 2
- 206010012289 Dementia Diseases 0.000 description 6
- 230000006996 mental state Effects 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 238000013145 classification model Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000003925 brain function Effects 0.000 description 2
- 230000003930 cognitive ability Effects 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- 230000001771 impaired effect Effects 0.000 description 2
- 230000000284 resting effect Effects 0.000 description 2
- 208000024891 symptom Diseases 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 230000001684 chronic effect Effects 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 230000001149 cognitive effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000002599 functional magnetic resonance imaging Methods 0.000 description 1
- 208000018879 impaired coordination Diseases 0.000 description 1
- 230000002427 irreversible effect Effects 0.000 description 1
- 238000002595 magnetic resonance imaging Methods 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000004770 neurodegeneration Effects 0.000 description 1
- 208000015122 neurodegenerative disease Diseases 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
Classifications
-
- 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
- A61B5/4076—Diagnosing or monitoring particular conditions of the nervous system
- A61B5/4088—Diagnosing of monitoring cognitive diseases, e.g. Alzheimer, prion diseases or dementia
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0033—Features or image-related aspects of imaging apparatus classified in A61B5/00, e.g. for MRI, optical tomography or impedance tomography apparatus; arrangements of imaging apparatus in a room
- A61B5/004—Features or image-related aspects of imaging apparatus classified in A61B5/00, e.g. for MRI, optical tomography or impedance tomography apparatus; arrangements of imaging apparatus in a room adapted for image acquisition of a particular organ or body part
- A61B5/0042—Features or image-related aspects of imaging apparatus classified in A61B5/00, e.g. for MRI, optical tomography or impedance tomography apparatus; arrangements of imaging apparatus in a room adapted for image acquisition of a particular organ or body part for the brain
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/05—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
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Animal Behavior & Ethology (AREA)
- Veterinary Medicine (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Neurology (AREA)
- Surgery (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Radiology & Medical Imaging (AREA)
- Artificial Intelligence (AREA)
- Psychiatry (AREA)
- Physiology (AREA)
- Neurosurgery (AREA)
- Psychology (AREA)
- High Energy & Nuclear Physics (AREA)
- Child & Adolescent Psychology (AREA)
- Developmental Disabilities (AREA)
- Hospice & Palliative Care (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Magnetic Resonance Imaging Apparatus (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention discloses a hypothesis-driven cognitive impairment brain network analysis method, which comprises the following steps: preprocessing the construction of a brain connectivity matrix; performing complex brain network measurement; hypothesis testing and variability analysis; the supervising machine performs learning verification. According to the technical scheme, aiming at the health control group, early-stage mild cognitive impairment patients and advanced mild cognitive impairment patients and Alzheimer disease patients, progressive hypothesis relations of brain network changes among different degrees of cognitive impairment patients are fully utilized, the quality of a cognitive impairment recognition model is improved, the model priori conditions are used for guiding selection of different brain region metric values, two possibly existing complex brain network topology metric relations are set as priori conditions of feature selection in machine learning, the constraint conditions of feature selection are used, blindness and randomness in the model optimization solving process are effectively avoided, time expenditure is reduced, and the model interpretability is improved.
Description
Technical Field
The invention relates to the technical field of cognitive science, in particular to a hypothesis-driven cognitive impairment brain network analysis method.
Background
Alzheimer's disease is a chronic, progressively worsening and irreversible neurodegenerative disease. Patients often suffer from hypomnesis, impaired hearing and vision, impaired speech, impaired coordination of movements, and gradually lose physical function as the condition progresses, ultimately leading to death. Patients with cognitive impairment to different degrees can be grouped through subjective psychology evaluation scores, for example, the simple mental state examination score is between 24 and 30, the dementia index is 0, and the crowd without symptoms such as depression, dementia and the like is divided into groups with normal cognitive ability; for simple mental state examination scores between 24 and 30, the dementia index is 0.5, the WMSLM II score is between 9 and 11 when the education level is greater than 16 years, or the WMSLM II score is between 6 and 9 when the education level is 8 to 15 years, or the WMSLM II score is between 3 and 6 when the education level is 0 to 7 years, and patients are actively informed that the memory is reduced but the daily life is not affected, and the patients without dementia symptoms are classified as early-stage mild cognitive impairment; for patients with simple mental state examination scores between 24 and 40, dementia index of 0.5, WMSLM ii score of less than 8 when education level is greater than 16 years, WMSLM ii score of less than 4 when education level is 8-15 years, or WMSLM ii score of less than 2 when education level is 0-7 years, and the patients are classified as advanced mild cognitive impairment; patients with a simple mental state examination score between 20 and 26 and a dementia index between 0.5 and 1 are classified as Alzheimer's disease.
In addition to gradual changes in cognitive dysfunction shown by patient conditions and clinical psychological scores, the existing research results show that similar phenomena exist in classification and identification of cognitive dysfunction, the classification accuracy between Alzheimer disease patients and a healthy control group is highest, the identification difficulty is minimum, the difference is maximum, and the classification results of early-stage mild cognitive dysfunction patients and late-stage mild cognitive dysfunction patients are worst, and the difficulty is maximum. This progressive relationship also exists in the different group pairwise recognition models.
Chinese patent document CN107909117B discloses a "classification device for early-late mild cognitive impairment based on brain function network characteristics". Firstly, preprocessing sample data, extracting a plurality of brain region time sequences, adopting pearson correlation to calculate correlation coefficients between the brain region time sequences to construct a brain function network, and calculating brain network parameters. And extracting features by adopting a step-by-step analysis method, training a binary classifier, extracting corresponding feature vectors from resting state functional magnetic resonance data to be classified, and inputting the feature vectors into the trained binary classifier to obtain a medical image classification result. The technical scheme does not set constraint conditions for feature selection, and blindness and randomness increase time overhead in the model optimization solving process.
Disclosure of Invention
The invention mainly solves the technical problem of insufficient classification capability of the prior technical scheme on cognition disorder patients, provides a hypothesis-driven cognition disorder brain network analysis method, aims at the cognition capability of four groups from early mild cognition disorder patients to late mild cognition disorder patients to Alzheimer disease patients in a healthy control group, fully utilizes progressive hypothesis relations of brain network changes among cognition disorder patients of different degrees, improves cognition disorder recognition model quality, guides selection of different brain region metric values as model priori conditions, and sets two possible complex brain network topology metric relations: gradually increasing (HC < EMCI < LMCI < AD) or gradually decreasing (HC > EMCI > LMCI > AD), and carrying out statistical test to serve as a priori condition of feature selection in machine learning, wherein the priori condition is used as a constraint condition of feature selection, so that blindness and randomness in the model optimization solving process can be effectively avoided, time cost is reduced, and the model interpretation is improved more easily.
The technical problems of the invention are mainly solved by the following technical proposal: the invention comprises the following steps:
s1, preprocessing the construction of a brain connectivity matrix; and calculating a coefficient brain connection matrix by adopting multi-mode brain partition.
S2, measuring a complex brain network;
s3, hypothesis testing and variability analysis; and acquiring a candidate brain region characteristic set in subsequent machine learning.
And S4, supervising the machine to perform learning verification.
Preferably, the step S1 preprocessing performs functional region segmentation on the human brain according to the multi-mode brain partitioning method of washington university, and subdivides the whole brain into 360 brain regions, and the specific operations include: s1.1, acquiring structural state and functional state magnetic resonance data and magnetic field distribution information of imaging equipment;
s1.2, registering a human brain into a CIFTI space according to acquired information to form 3.2 ten thousand coordinate points;
s1.3, registering the brain into a multi-mode brain partition by adopting a J-HCPHMP method to form left and right 180 brain sub-regions;
s1.4, performing correlation analysis on functional magnetic resonance data among 360 brain areas to form a 360X 360 complex brain network adjacency matrix;
s1.5, thresholding is carried out on the complex brain network adjacency matrix to remove noise and interference information, and dense brain connection is changed into sparse brain connection.
Preferably, the step S2 of performing complex brain network metrics specifically includes:
s2.1, constructing two complex brain networks: a weighted brain network and a binarized brain network;
s2.2, 7 global measurement indexes in the weighted brain network are calculated;
s2.3, 7 regional measurement indexes in the weighted brain network are calculated;
s2.4, 8 regional measurement indexes in the binary brain network are calculated.
Preferably, the weighted brain network corresponds to a sparse brain connection matrix, and the binarized brain network sets the effective connection in the weighted brain network to 1, sets the other connections to 0, and resets the connection weight on the diagonal to 0.
Preferably, the step S2.2 calculates 7 global metrics in the weighted brain network, including global efficiency of the complex brain network, maximizing module, number of best modules, homography coefficient, small world characteristic index, characteristic path length, and average aggregation coefficient.
Preferably, the step S2.3 calculates 7 regional measurement indexes in the weighted brain network, including degree, intensity, aggregation coefficient, local efficiency, median centrality, feature vector centrality and page ranking centrality of each node of the complex brain network.
Preferably, the step S2.4 calculates 8 regional measurement indexes in the binary brain network, including node degree, aggregation coefficient, local efficiency, median centrality, feature vector centrality, page order centrality, K core centrality and flow coefficient of the brain network.
Preferably, the step S3 hypothesis test and variability analysis is specifically as follows:
calculating the relation value satisfying progressive monotone change in all network topology values, and screening out the brain region where the measurement value is located, as shown in formula (1):
wherein AD is Alzheimer disease patient, LMCI is late stage mild cognitive impairment patient, EMCI is early stage mild cognitive impairment patient, HC is healthy control group,
the brain region exhibiting a significantly progressive change relationship under statistical test is calculated as shown in formula (2):
U 2 ＝{Area|P(KruskalWallis H test(Measure(Area))＜Criteria} (2)
calculation U 1 And U 2 The intersection of the two sets serves as a candidate brain region feature set in subsequent machine learning.
Preferably, the step S4 specifically includes:
s4.1, filtering and screening the candidate brain regions selected in the step S3 by adopting characteristic engineering;
s4.2, modeling the characteristic values selected in the characteristic engineering by adopting a machine learning algorithm;
s4.3, adopting a multi-class identification strategy to improve the classification performance of the support vector machine.
Preferably, the step S4.1 screening method includes a filtering type feature selection algorithm and a package type feature selection algorithm.
The beneficial effects of the invention are as follows: aiming at the health control group, the cognitive ability of the early-stage mild cognitive impairment patients and the late-stage mild cognitive impairment patients in the four groups of Alzheimer disease patients is fully utilized, the progressive assumption relation of brain network changes among the cognitive impairment patients with different degrees is improved, the quality of a cognitive impairment recognition model is improved, the model prior condition is used for guiding the selection of different brain region metric values, and two possibly existing complex brain network topology metric relations are set: gradually increasing (HC < EMCI < LMCI < AD) or gradually decreasing (HC > EMCI > LMCI > AD), and carrying out statistical test to be used as a priori condition of feature selection in machine learning, taking the priori condition as a constraint condition of feature selection, can effectively avoid blindness and randomness in the model optimization solving process, simultaneously reduce time cost, is more beneficial to improving the model interpretation,
the complex brain network measurement variation coefficients of the cognitive impairment patients and healthy people with different degrees are calculated, the assumption of progressive monotone change rules between two groups is provided, and 30 characteristic values in 20 brain areas are extracted by adopting a statistical test mode. Most relevant brain regions are located in frontal and islets, and one of the banded brain regions was first found to be closely associated with cognitive impairment. The 30 features are used as prior conditions of machine learning for model training, so that high-level two-classification, three-classification and even more than 50% four-classification are finally realized, and classification results are obviously superior to other related researches. It is also further demonstrated that the ADNI dataset refines mild cognitive impairment patients to early and late justification.
Drawings
Fig. 1 is a diagram of a brain network analysis method for hypothetically driven cognitive impairment according to the present invention.
FIG. 2 is a graph showing the results of brain partitioning achieved by the J-HCPHMMP method of the present invention.
Fig. 3 is a diagram of a weighted brain connection matrix and a binarized brain connection matrix of the present invention.
Fig. 4 is a global metric diagram of a complex brain network of the present invention.
Fig. 5 is a graph of a complex brain network region metric of the present invention.
FIG. 6 is a plot of brain regions exhibiting progressive monotonic changes in a weighted complex brain network in accordance with the present invention.
Fig. 7 is a representation of a multi-classification model of cognitive impairment according to the present invention.
Detailed Description
The technical scheme of the invention is further specifically described below through examples and with reference to the accompanying drawings.
Examples: the method for analyzing the brain network of the cognitive impairment under the assumption of driving in the embodiment, as shown in fig. 1, comprises the following steps:
s1, preprocessing the construction of a brain connectivity matrix;
the calculation of the coefficient brain connection matrix by adopting the multi-mode brain partition in the step 1 comprises the following specific operations:
and 1-1, acquiring magnetic resonance data. The specific parameters of the structural magnetic resonance imaging are sagittal plane T1 weight three-dimensional rapid gradient echo imaging (T1W-3D-MPRAGE), an eight-surface coil SENSE parallel imaging algorithm is adopted, the external magnetic field intensity is 3 Tesla, the imaging resolution is 256 multiplied by 256.1.0 mm, the number of slices is 170, and the slice thickness is 1.2 mm. The echo time TR is set to 6.78 milliseconds and the repetition time TE is set to 3.14 milliseconds. The specific parameters of the functional magnetic resonance imaging are that the external magnetic field intensity of 3 tesla is adopted under the resting state of the subject, the imaging resolution is 64 multiplied by 64.3125 mm, the number of slices is 48, the thickness of the slices is 3.313 mm, and 140 time sequences are acquired for 6720 slices in total. The echo time TR is set to 3000 ms and the repetition time TE to 30 ms. Structural and functional magnetic resonance data were processed into the cifi space using the J-hcmmp data preprocessing method, as shown in fig. 2.
1-2, weighting and binarizing the 360×360 complex brain network adjacency matrix by using thresholding, as shown in fig. 3. The weighted brain network corresponds to the sparse brain connection matrix calculated in the step one; the binarized brain network is configured such that the effective connection in the weighted brain network is set to 1 and the other connections are set to 0. Meanwhile, the connection weight located on the diagonal line is reset to 0.
S2, measuring a complex brain network;
the complex brain network measurement method in the step 2 specifically comprises the following steps:
2-1. According to the weighted sum binary brain connection matrix calculated in the step 1, the measurement indexes under each brain region are calculated respectively by using a BCT tool box, wherein the global indexes are as shown in fig. 4:
2-2. According to the weighted and binarized brain connection matrix calculated in the step 1, respectively calculating the measurement indexes under each brain region by using a BCT tool box, wherein the regional indexes are shown in fig. 4:
s3, hypothesis testing and variability analysis;
the hypothesis testing and variability analysis described in step 3 is specifically as follows:
3-1, calculating relation values meeting progressive monotone change in all network topology values, and screening out brain areas where the measurement values are located, wherein the relation values are shown in a formula (1):
fig. 6 is a graph of brain region distribution results in a weighted complex brain network exhibiting progressive monotonic changes.
3-2, calculating brain regions showing significant progressive transformation relations under statistical test, as shown in formula (2):
U 2 ＝{Area|P(KruskalWallis H test(Measure(Area))＜Criteria} (2)
3-3. Calculate U 1 And U 2 The intersection of the two sets serves as a candidate brain region feature set in subsequent machine learning.
And S4, supervising the machine to perform learning verification.
The supervised machine learning validation described in step 4 is specifically as follows:
4-1, filtering and screening the candidate brain regions selected in the step 3 by adopting characteristic engineering. The screening modes are two, namely a filtering type characteristic selection algorithm and a parcel type characteristic selection algorithm. By adopting the two algorithms, the dimension of the feature data can be reduced, and the training complexity of the model can be reduced.
And 4-2, modeling the selected characteristic values in the characteristic engineering by adopting a machine learning algorithm. The invention adopts a support vector machine.
4-3, adopting a multi-class identification strategy to improve the classification performance of the support vector machine.
The multi-classification model of cognitive disorder realized by the invention is shown in fig. 7, and the ROC curve of the multi-classification model in fig. 7. (a) HC vs. emci vs. lmci; (B) EMCI vs. lmci vs. ad; (C) HC vs. EMCI vs. LMCI vs. AD; (D) HC vs. (EMCI and LMCI) vs. ad.
The invention calculates the complex brain network measurement variation coefficients of patients with different degrees of cognitive impairment and healthy people, proposes the assumption of progressive monotone change rules between two groups, and adopts a statistical test mode to extract 30 characteristic values in 20 brain areas. Most relevant brain regions are located in frontal and islets, and we first found that one of the banded brain regions is closely associated with cognitive impairment. Model training is carried out by taking the 30 features as prior conditions of machine learning, and finally, four classification of higher level of two classification, three classification and even more than 50% is realized, and classification results are obviously superior to other related researches. At the same time we further demonstrate the rationality of the ADNI dataset to refine mild cognitive impairment patients into early and late stages.
The specific embodiments described herein are offered by way of example only to illustrate the spirit of the invention. Those skilled in the art may make various modifications or additions to the described embodiments or substitutions thereof without departing from the spirit of the invention or exceeding the scope of the invention as defined in the accompanying claims.
Although terms such as connectivity matrix to the brain, complex brain network metrics, etc. are used more herein, the possibility of using other terms is not precluded. These terms are used merely for convenience in describing and explaining the nature of the invention; they are to be interpreted as any additional limitation that is not inconsistent with the spirit of the present invention.
Claims (3)
1. A hypothesis-driven cognitive impairment brain network analysis method, comprising the steps of:
s1, preprocessing construction of a brain connectivity matrix, wherein the preprocessing is used for carrying out functional region segmentation on human brains according to a multi-mode brain partitioning method of Washington university, and subdividing the whole brains into 360 brain regions, and the specific operation comprises the following steps:
s1.1, acquiring structural state and functional state magnetic resonance data and magnetic field distribution information of imaging equipment;
s1.2, registering a human brain into a CIFTI space according to acquired information to form 3.2 ten thousand coordinate points;
s1.3, registering the brain into a multi-mode brain partition by adopting a J-HCPHMP method to form left and right 180 brain sub-regions;
s1.4, performing correlation analysis on functional magnetic resonance data among 360 brain areas to form a 360X 360 complex brain network adjacency matrix;
s1.5, performing threshold processing on the complex brain network adjacency matrix to remove noise and interference information, and changing dense brain connection into sparse brain connection;
s2, complex brain network measurement is carried out, and the method specifically comprises the following steps:
s2.1, constructing two complex brain networks: a weighted brain network and a binarized brain network;
s2.2, 7 global measurement indexes in the weighted brain network are calculated, wherein the global measurement indexes comprise global efficiency, a maximization module, the number of optimal modules, homozygosity coefficients, small world characteristic indexes, characteristic path lengths and average aggregation coefficients of the complex brain network;
s2.3, 7 regional measurement indexes in the weighted brain network are calculated, wherein the regional measurement indexes comprise node degree, intensity, aggregation coefficient, local efficiency, medium number centrality, feature vector centrality and page ordering centrality of the complex brain network;
s2.4, 8 regional measurement indexes in a binary brain network are calculated, wherein the regional measurement indexes comprise node degree, aggregation coefficient, local efficiency, medium number centrality, feature vector centrality, page ordering centrality, K core centrality and flow coefficient of the brain network;
s3, hypothesis testing and variability analysis, which is specifically as follows:
calculating the relation value satisfying progressive monotone change in all network topology values, and screening out the brain region where the measurement value is located, as shown in formula (1):
wherein AD is Alzheimer disease patient, LMCI is late stage mild cognitive impairment patient, EMCI is early stage mild cognitive impairment patient, HC is healthy control group,
the brain region exhibiting a significantly progressive change relationship under statistical test is calculated as shown in formula (2):
U 2 ＝{Area|P(KruskalWallis H test(Measure(Aea))<Criterta} (2)
calculation U 1 And U 2 An intersection of the two sets is used as a candidate brain region feature set in subsequent machine learning;
s4, supervising the machine to perform learning verification, and specifically comprising the following steps:
s4.1, filtering and screening the candidate brain regions selected in the step S3 by adopting characteristic engineering;
s4.2, modeling the characteristic values selected in the characteristic engineering by adopting a machine learning algorithm;
s4.3, adopting a multi-class identification strategy to improve the classification performance of the support vector machine.
2. The hypothesis-driven cognitive impairment brain network analysis method of claim 1, wherein the weighted brain network corresponds to a sparse brain connection matrix, the binarized brain network sets active connections in the weighted brain network to 1, other connections to 0, and sets connection weights on a diagonal to 0.
3. The hypothesis-driven brain network analysis method according to claim 1, wherein the step S4.1 screening method includes a filtering feature selection algorithm and a parcel feature selection algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110653150.2A CN113558602B (en) | 2021-06-11 | 2021-06-11 | Hypothesis-driven cognitive impairment brain network analysis method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110653150.2A CN113558602B (en) | 2021-06-11 | 2021-06-11 | Hypothesis-driven cognitive impairment brain network analysis method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113558602A CN113558602A (en) | 2021-10-29 |
| CN113558602B true CN113558602B (en) | 2023-11-14 |
Family
ID=78161959
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110653150.2A Active CN113558602B (en) | 2021-06-11 | 2021-06-11 | Hypothesis-driven cognitive impairment brain network analysis method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113558602B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114864051B (en) * | 2022-07-06 | 2022-10-04 | 北京智精灵科技有限公司 | Cognitive improvement method and system based on neural network |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110326054A (en) * | 2017-02-27 | 2019-10-11 | 雷恩第一大学 | Determine the method, apparatus and program for participating in executing at least one brain network of given process |
| CN111063423A (en) * | 2019-12-16 | 2020-04-24 | 哈尔滨工程大学 | Method for extracting specific structure of brain network of Alzheimer disease and mild cognitive impairment |
| CN111402198A (en) * | 2020-02-11 | 2020-07-10 | 山东师范大学 | Alzheimer disease classification method and system based on anatomical landmarks and residual error network |
| CN112348833A (en) * | 2020-11-06 | 2021-02-09 | 浙江传媒学院 | Brain function network variation identification method and system based on dynamic connection |
-
2021
- 2021-06-11 CN CN202110653150.2A patent/CN113558602B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110326054A (en) * | 2017-02-27 | 2019-10-11 | 雷恩第一大学 | Determine the method, apparatus and program for participating in executing at least one brain network of given process |
| CN111063423A (en) * | 2019-12-16 | 2020-04-24 | 哈尔滨工程大学 | Method for extracting specific structure of brain network of Alzheimer disease and mild cognitive impairment |
| CN111402198A (en) * | 2020-02-11 | 2020-07-10 | 山东师范大学 | Alzheimer disease classification method and system based on anatomical landmarks and residual error network |
| CN112348833A (en) * | 2020-11-06 | 2021-02-09 | 浙江传媒学院 | Brain function network variation identification method and system based on dynamic connection |
Non-Patent Citations (4)
| Title |
|---|
| Jingwan Jiang.Deep learning based mild cognitive impairment diagnosis using structure MR images.Neuroscience Letters.2020,1-7. * |
| Jinhua Sheng.A novel joint HCPMMP method for automatically classifying Alzheimer’s and different stage MCI patients.Behavioural Brain Research.2019,210-221. * |
| Jinhua Sheng.Alzheimer’s disease, mild cognitive impairment, and normal aging distinguished by multi-modal parcellation and machine learning.Scientific Reports.2020,1-10. * |
| R. Chaves, J. Ramírez.SVM-based computer-aided diagnosis of the Alzheimer’s disease using t-test NMSE feature selection with feature correlation weighting.Neuroscience Letters.2009,293–297. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113558602A (en) | 2021-10-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110443798B (en) | Autism detection method, device and system based on magnetic resonance image | |
| Farooq et al. | A deep CNN based multi-class classification of Alzheimer's disease using MRI | |
| CN113616184B (en) | Brain network modeling and individual prediction method based on multi-mode magnetic resonance image | |
| CN113558603B (en) | Multi-modal cognitive disorder recognition method based on deep learning | |
| Yue et al. | Auto-detection of Alzheimer's disease using deep convolutional neural networks | |
| CN110598793B (en) | Brain function network feature classification method | |
| CN107506761A (en) | Brain image dividing method and system based on notable inquiry learning convolutional neural networks | |
| CN111009321A (en) | Application method of machine learning classification model in juvenile autism auxiliary diagnosis | |
| CN110532907A (en) | Based on face as the Chinese medicine human body constitution classification method with tongue picture bimodal feature extraction | |
| CN113558602B (en) | Hypothesis-driven cognitive impairment brain network analysis method | |
| CN114926477A (en) | Brain tumor multi-modal MRI (magnetic resonance imaging) image segmentation method based on deep learning | |
| CN114469120A (en) | Multi-scale Dtw-BiLstm-Gan electrocardiosignal generation method based on similarity threshold migration | |
| Shrivastava et al. | Control or autism-classification using convolutional neural networks on functional MRI | |
| Irmak | A novel implementation of deep-learning approach on malaria parasite detection from thin blood cell images | |
| CN104463885B (en) | A kind of Multiple Sclerosis lesions region segmentation method | |
| CN111540467A (en) | Schizophrenia classification identification method, operation control device and medical equipment | |
| CN113705670A (en) | Brain image classification method and device based on magnetic resonance imaging and deep learning | |
| CN112863664A (en) | Alzheimer disease classification method based on multi-modal hypergraph convolutional neural network | |
| CN116797817A (en) | Autism disease prediction technology based on self-supervision graph convolution model | |
| CN113283465B (en) | Diffusion tensor imaging data analysis method and device | |
| CN112561935B (en) | Intelligent classification method, device and equipment for brain images | |
| CN108256569A (en) | A kind of object identifying method under complex background and the computer technology used | |
| Pavalarajan et al. | Detection of Alzheimer's disease at Early Stage using Machine Learning | |
| Smith et al. | Implicit context representation Cartesian genetic programming for the assessment of visuo-spatial ability | |
| Rohit et al. | A Novel Approach for Content based Mri Brain Image Retrieval |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |