CN117095812A

CN117095812A - A method, system, equipment and medium for identifying the cognitive level of patients with mild brain trauma

Info

Publication number: CN117095812A
Application number: CN202311053701.7A
Authority: CN
Inventors: 白丽君; 李旋
Original assignee: Xian Jiaotong University
Current assignee: Xian Jiaotong University
Priority date: 2023-08-21
Filing date: 2023-08-21
Publication date: 2023-11-21

Abstract

The invention discloses a method, system, equipment and medium for identifying the cognitive level of patients with mild brain trauma, and belongs to the field of medical imaging technology. Extract the time series signals in the ternary network and conduct dynamic analysis; build a dynamic brain pattern model based on the dynamic analysis results, and extract dynamic indicators from the dynamic brain pattern model; extract based on the cognitive scale of patients with mild brain trauma The dynamic indexes are used to group the cognitive levels of patients with mild brain trauma and identify the cognitive levels of patients with mild brain trauma; one-way analysis of variance is used to compare the dynamic index values of patients with mild brain trauma at different cognitive levels. Validating the accuracy of identified cognitive levels in patients with mild traumatic brain injury. This method can be applied to identify different cognitive levels of patients with mild brain trauma, providing an effective auxiliary detection method for the early identification of cognitive problems with mild brain trauma.

Description

Method, system, equipment and medium for identifying cognitive level of patient with mild brain trauma

Technical Field

The invention belongs to the technical field of medical imaging, and particularly relates to a method, a system, equipment and a medium for identifying the cognitive level of a patient with mild cerebral trauma.

Background

Most of the traumatic brain injuries (traumatic brain injury, TBI) are mild traumatic brain injuries (also known as concussions). Traumatic brain injury is characterized by significant heterogeneity, variable progression, and poor prognosis, i.e., cognitive problems. The exploration of sources of variation in clinical symptoms, behavioral phenotype expression and their underlying neural basis has attracted much attention. TBI can cause traumatic axonal injury and disrupt the coordination within the large-scale brain network.

There is a theory that proposes a ternary network model, i.e. a Salience Network (SN) that regulates interactions with a central executive network (central executive network, CEN) and a default mode network (default mode network, DMN). Ternary network models assume that the abnormal functional organization of these brain networks and their dynamic cross-network interactions are the basis for a range of neurological diseases including TBI. SN integrates cognitive and sensory information and serves as an interface between DMN and CEN, coordinating internal psychological processes with external stimulus driven cognitive processes. Previous studies have utilized a three-network model of stable functional connection analysis to find that structural connections within a damaged SN can disrupt the regulation of the relevant network, especially the inactivation of DMN, resulting in insufficient cognitive control capacity of TBI. While a number of studies have assumed that the functional connections (function connectivity, FC) are stable throughout the scan, the time-varying interactions between these brain networks and their correlation with cognitive impairment are still unclear.

Although previous studies have demonstrated a close link between ternary networks and cognitive impairment, there is still a lack of a theoretical framework to study how brain cognitive network abnormalities affect human cognition and lead to major neurobiological symptoms.

Disclosure of Invention

In order to overcome the defects in the prior art, the invention aims to provide a method, a system, a device and a medium for identifying the cognitive level of a patient with mild brain trauma, which provide an effective auxiliary detection means for early identification of the cognitive problem of the patient with mild brain trauma.

In order to achieve the above purpose, the invention is realized by adopting the following technical scheme:

the invention discloses a method for identifying cognitive level of a patient with mild cerebral trauma, which comprises the steps of extracting time sequence signals in a ternary network and carrying out dynamic analysis; constructing a dynamic brain pattern model according to the dynamic analysis result, and extracting dynamic indexes from the dynamic brain pattern model; the cognitive level of the patient with mild brain trauma is identified by grouping the cognitive level of the patient with mild brain trauma according to the cognitive scale of the patient with mild brain trauma and the extracted dynamic index.

Preferably, the ternary network is obtained by independent component analysis of resting functional magnetic resonance imaging data of a patient with mild brain trauma.

Further preferably, the method further comprises the steps of collecting structural data, and performing slice timing time correction and realign head motion correction on time points in the resting-state functional magnetic resonance imaging data before independent component analysis to obtain calibrated images; registering the T1 structural data coregister on the obtained functional image, and obtaining the preprocessed data by segmentation, covariate regression, band-pass filtering, spatial normalization and spatial smoothing.

Preferably, the step of independent component analysis is: the method comprises the steps of performing dimension reduction on resting state functional magnetic resonance imaging data of a patient with mild cerebral trauma by using two principal component analysis, using an Infomax algorithm, performing inversion reconstruction, obtaining the time histories and the space diagrams of the ICs tested by all the patient with mild cerebral trauma, converting the time histories and the space diagrams into z scores, and then selecting 5 ICs from the time histories and the space diagrams, wherein the 5 ICs correspond to a front default mode network, a rear default mode network, a left central execution network, a right central execution network and SN respectively;

wherein the front default mode network and the rear default mode network correspond to DMNs in the three network model, the left central execution network and the right central execution network correspond to CENs in the three network model, and the SN corresponds to SNs in the three network model.

Preferably, the extracted time-series signal is dynamically changed by adopting a sliding window dynamic function connection method or a hidden Markov chain method.

Preferably, the pearson correlation coefficient of each brain interval of the patient with mild cerebral trauma is obtained through dynamic analysis, and the dynamic index is calculated according to the pearson correlation coefficient.

Preferably, a neuropsychological measurement method is used to obtain a cognitive scale for a patient with mild brain trauma; in the neuropsychological measurement method, the state of each patient with mild cerebral trauma is divided into four cognitive domains, namely cognitive flexibility, executive function, working memory and language ability, the cognitive flexibility is measured by using a digital symbol coding score and a test A part of WAIS-III, the executive function is estimated by using a forward digital span of WAIS-III, the working memory is estimated by using a backward digital span of WAIS-III, and the language ability and the semantic memory are checked by using a language fluency test.

Further preferably, the evaluation criterion at the time of grouping is: for each cognitive domain, an average value of < 1.5SDs compared with the healthy control group is taken as no damage, and an average value of more than or equal to 1.5SDs compared with the healthy control group is taken as damage.

Further preferably, for damage, no cognitive domain damage is taken as no cognitive domain damage, one cognitive domain damage is taken as a single cognitive domain damage, and two or more cognitive domain damage are taken as multiple cognitive domain damage.

The invention also discloses a system for identifying the cognitive level of a patient with mild brain trauma, which comprises the following steps:

the extraction module is used for extracting time sequence signals in the ternary network and carrying out dynamic analysis; constructing a dynamic brain pattern model according to the dynamic analysis result, and extracting dynamic indexes from the dynamic brain pattern model;

the identification module is used for grouping the cognitive level of the mild brain trauma patient according to the cognitive scale of the mild brain trauma patient and the extracted dynamic index and identifying the cognitive level of the mild brain trauma patient.

The present invention also discloses a computer readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by a computing device, cause the computing device to perform any of the methods described above.

The invention also discloses a computing device comprising: one or more processors, memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs comprising instructions for performing any of the methods described above.

Compared with the prior art, the invention has the following beneficial effects:

According to the method for identifying the cognitive level of the patient with mild brain trauma, according to the characteristics that the brain trauma damages the coordination activity of the ternary network and damages the cognitive level in a plurality of cognitive domains, the dynamic function network and the relation between the dynamic function network and the cognitive dysfunction of the patient with mild brain trauma are researched by adopting a theoretical driving system neuroscience framework and the ternary network. The time sequence of the resting state functional magnetic resonance imaging data of all the patients with mild cerebral trauma is extracted from the ternary network, and the extracted time sequence is dynamically analyzed to obtain dynamic indexes so as to estimate network interaction in each dynamic sliding window. The three-way network is connected with the cognition of the mild brain trauma by means of the dynamic index, a dynamic model for distinguishing the cognition state of the mild brain trauma patient is constructed by calculating the obvious difference of the dynamic index values of the mild brain trauma patient in different cognition states, the cognition level of the mild brain trauma patient is identified, the cognition level of the mild brain trauma patient is helped to be clinically and further identified, and an effective auxiliary detection means is provided for early identification of the cognition problem of the mild brain trauma.

Further, the method of independent component analysis can identify large-scale networks in patients with combined mild brain trauma. The spatially independent component analysis can spatially separate brain regions independent of each other, providing an effective means for brain network analysis. The expanded algorithm set independent component analysis based on the space independent component analysis can perform dimension reduction processing on the resting state functional magnetic resonance imaging data of all patients with mild brain trauma, thereby obtaining general brain network division.

Drawings

FIG. 1 is a flow chart of a method of the present invention for identifying cognitive levels in a patient with mild brain trauma;

FIG. 2 is a schematic diagram of a computer device of the present invention;

FIG. 3 is a graph of recognition results of the method of the present invention for recognizing cognitive levels in a patient with mild brain trauma;

FIG. 4 is a schematic flow chart of a dynamic sliding window analysis of the method of the invention for identifying cognitive levels in a patient with mild brain trauma;

FIG. 5 is a graph of the correlation of NII values to a cognitive scale for a method of the invention for identifying cognitive levels in a patient with mild brain trauma; wherein A is the correlation analysis of NII and FDS, B is the correlation analysis of NII and TMT-A, C is the correlation analysis of NII and BDS, D is the correlation analysis of NII and DCS, E is the correlation analysis of NII and VF;

FIG. 6 is a graph showing the differences between NII values of slightly traumatic brain injury patients in different cognitive states in the method for identifying cognitive levels in slightly traumatic brain injury patients according to the present invention.

Wherein, 60-computer device; 61-a processor; 62-memory; 63-computer program.

Detailed Description

The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.

In the description of the present invention, it will be understood that the terms "comprises" and "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.

It is also to be understood that the terminology used in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.

It should be further understood that the term "and/or" as used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations, e.g., a and/or B, may represent: a exists alone, A and B exist together, and B exists alone. In addition, the character "/" herein generally indicates that the front and rear associated objects are an "or" relationship.

It should be understood that although the terms first, second, third, etc. may be used to describe the preset ranges, etc. in the embodiments of the present invention, these preset ranges should not be limited to these terms. These terms are only used to distinguish one preset range from another. For example, a first preset range may also be referred to as a second preset range, and similarly, a second preset range may also be referred to as a first preset range without departing from the scope of embodiments of the present invention.

Depending on the context, the word "if" as used herein may be interpreted as "at … …" or "at … …" or "in response to a determination" or "in response to detection". Similarly, the phrase "if determined" or "if detected (stated condition or event)" may be interpreted as "when determined" or "in response to determination" or "when detected (stated condition or event)" or "in response to detection (stated condition or event), depending on the context.

Various structural schematic diagrams according to the disclosed embodiments of the present invention are shown in the accompanying drawings. The figures are not drawn to scale, wherein certain details are exaggerated for clarity of presentation and may have been omitted. The shapes of the various regions, layers and their relative sizes, positional relationships shown in the drawings are merely exemplary, may in practice deviate due to manufacturing tolerances or technical limitations, and one skilled in the art may additionally design regions/layers having different shapes, sizes, relative positions as actually required.

As shown in fig. 1, the method for identifying the cognitive level of the patient with mild brain trauma provided by the invention is characterized in that functional data of the patient with mild brain trauma is collected and preprocessed, and the preprocessed data is subjected to independent component analysis to determine a ternary network; extracting time sequence signals in a ternary network, and carrying out dynamic analysis; then constructing a dynamic brain pattern model according to the dynamic analysis result, and extracting dynamic indexes from the dynamic brain pattern model; identifying a cognitive level of the patient with mild brain trauma according to the classification of the cognitive level of the patient with mild brain trauma and the extracted dynamic index; and (3) carrying out statistical comparison on dynamic indexes of mild cerebral trauma patients with different cognitive states so as to verify the accuracy of the model. The method comprises the following specific steps:

1. collecting data

Resting functional magnetic resonance imaging (fMRI, functional Magnetic Resonance Imaging) data and high resolution structural data of a patient with mild brain trauma are acquired using an MRI scanner, with the first 5 time points in the acquired raw fMRI data removed.

2. Construction of dynamic brain pattern model

S1: preprocessing the acquired data

1) Performing slice timing time correction on time points in the remaining fMRI data, and correcting interlayer time differences generated by interlayer scanning of each patient with mild cerebral trauma under each time point; then, performing realign head movement correction to reduce interference of head movement of a patient with mild cerebral trauma caused by resting fMRI data during scanning, and obtaining a calibrated image;

2) Registering the acquired T1 structural data coregister on the calibrated image in the step 1), dividing the image to form gray matter, white Matter (WM) and cerebrospinal fluid (CSF), and then carrying out covariate regression; the specific steps of the regression of the covariates are as follows:

a. regression of the noise signal, removing linear drift;

b. regression of the average time series signal of WM and CSF masks and global signal;

c. to reduce the influence of head movements, the translational and rotational amounts in the x, y and z directions are regressed by using a friston24 head movement parameter model. To further reduce the effects of head movements, the interframe shift (frame-wise displacement, FD) value for each patient with mild brain trauma may also be calculated in head motion scrubbing regressors, the bad time points thresholded to FD > 1mm, and the time points at which each shift is too large returned as covariates.

3) After covariate regression is completed, band-pass filtering of 0.01-0.1 Hz is carried out on fMRI data; then spatially normalizing the fMRI data, registering the fMRI data to a Montreal standard spatial template using EPI templates, and the voxel size after spatial resampling is set to be 3 multiplied by 3mm ³ The method comprises the steps of carrying out a first treatment on the surface of the Finally, an isotropic half-height full-width Gaussian kernel (6X 6 mm) ³ ) And performing smoothspace smoothing on the fMRI data to obtain preprocessed fMRI data.

S2: independent component analysis is carried out on the preprocessed data to determine a ternary network

Independent component analysis in signal processing, the multi-component mixed signal is decomposed into linear stacks of independent components (independent components, ICs), and the decomposed ICs are considered to contain more useful information. Independent component analysis also assumes that the independent component is a non-gaussian signal, proving available, as long as the source signal is non-gaussian, the decomposition result of the independent component is unique; if the source signal is gaussian, the decomposition result will be infinite. Independent component analysis it is assumed that the observed mixed signal X can be written AS x=as, where S is an unknown source signal with mutually independent components, a is an unknown mixed matrix, and ICA is to statistically estimate the source signal S and the mixed matrix a with only X known. Specifically, independent component analysis typically selects a sigmoid function as the cumulative distribution function of the original dataset, and iteratively finds the separation matrix using maximum likelihood estimates.

And (3) performing dimension reduction processing on the preprocessed fMRI data obtained in the step S1 based on the extended algorithm group independent component analysis (group independent component analysis, gICA) of the space independent component analysis (independent component analysis, ICA) by using GIFT software, and determining a ternary network.

The method comprises the following specific steps: first, the fMRI data after S1 preprocessing is reduced in dimension by two Principal Component Analysis (PCA), the collected data is reduced to a target component, and the target component number is determined according to a minimum description length criterion. The Infomax algorithm is then used in the independent component (independent components, ICs) estimation. And secondly, carrying out inversion reconstruction on tested components of the mild brain trauma patient by adopting a double regression method, obtaining the ICS time histories and the space diagrams of all the tested mild brain trauma patient by inversion reconstruction, and converting the specific map of the tested mild brain trauma patient into a z score. Finally, according to the existing study on brain anatomy and its corresponding functions, 5 ICs are selected from the ICs corresponding to the front default mode network (acmn), the rear default mode network (pDMN), the left central executive network (lCEN), the right central executive network (rCEN) and SN, respectively, to the DMN, CEN and SN of the three network model.

S3: extracting time sequence signals from ternary network and dynamically analyzing

Based on the determined ternary network, extracting fMRI time series of all patients with mild cerebral trauma tested in the ternary network, and carrying out dynamic analysis according to the extracted time series signals.

In order to study the time-varying cross-network interaction of the ternary network, a sliding window dynamic function connection method is adopted to carry out data dynamization, and the method specifically comprises the following steps: first, the window width is set to w and the step length is set to s. Units: TR. TR is the pulse repetition time (time of repetition), which refers to the time required to scan a whole brain. Then, the time series of each brain region is segmented by using a sliding window, wherein the range of the first window is from the 1 st time point to the w th time point, the second window is from the 1 st+s time point to the w+s time point, the third window is from the 1 st+2s time point to the w+2s time point, and the like, so as to obtain the division of all the time windows. Thereafter at each windowInternally calculating Pearson correlation coefficient-CC of each brain interval _SN,CEN And CC _SN,DMN The CC _SN,CEN Is the correlation between the time sequences of SN and CEN, the CC _SN,DMN Is the correlation between the time series of SN and DMN, and a dynamic functional connection matrix is formed by the pearson correlation coefficients of the respective brain intervals calculated. By repeating the process of intercepting the window and calculating the correlation value, a functional connection matrix within the whole time period can be obtained.

Furthermore, the method for performing data dynamization includes, but is not limited to, a sliding window dynamic function connection method, for example, a hidden markov chain method may also be used for performing data dynamization.

S4: dynamic brain pattern model is built according to dynamic analysis results, and dynamic indexes, namely brain-specific network interaction indexes (network interaction index, NII) are extracted

Considering the core role of SN in generating causal control signals that initiate dynamic switching between CEN and DMN, network interactions in each dynamic sliding window are estimated by measuring NII.

The method comprises the following specific steps: piercan correlation coefficient-CC based on S3 dynamic analysis _SN,CEN And CC _SN,DMN The dynamic index NII is calculated according to the following formula:

NII＝f(CC _SN,CEN )-f(CC _SN,DMN )

wherein,

here, CC is the Pearson correlation between two component network time series, CC _SN,CEN Is the correlation between the time series of SN and CEN. f (CC) computing Fisher-z transform of Pearson correlation between two component network time series, f (CC) _SN,CEN ) Calculating Pearson phase between time series of SN and CENFisher-z transform of the relationship. For double sided CEN, f (CC _SN,lCEN ) And f (CC) _SN,rCEN ) Then take the average value as f (CC _SN,CEN ). Pair f (CC) _SN,DMN ) The same procedure was also performed.

In the ternary network model, the greater the NII value, the more isolated the network interaction between the SN-CEN and SN-DMN systems.

3. Grouping cognitive levels in patients with mild brain trauma

The cognitive level of the patient with mild brain trauma is regrouped according to the cognitive scale of the patient and the dynamic index extracted in S4, so as to determine the cognitive level of the patient. The method comprises the following specific steps:

the cognitive scale uses neuropsychological measurement methods including i) the numerical symbolic coding score (Digital Symbol Coding, DSC) of the Weber adult mental scale (WAIS) -III and the test A section (Trail-Making Test Part A, TMT-A) for measuring cognitive flexibility; ii) forward digital span (Forward Digit Span, FDS) of WAIS-III for evaluating executive function; iii) The backward digital span (Backward Digit Span, BDS) of WAIS-III for evaluating working memory; iv) a language Fluency (VF) test for checking language ability and semantic memory.

To quantify the cognitive scores, each patient was evaluated for the extent of injury in different cognitive domains based on neuropsychological reports and test data. The specific steps of the evaluation are as follows: the status of each patient is divided into four aspects: cognitive flexibility, executive function, working memory, and linguistic ability. For each cognitive domain, the following scoring table is used: no damage, i.e. no significant damage (defined as mean < 1.5SDs with healthy control group); impaired, meaning reduced cognitive ability (defined as ≡1.5SDs compared to the average value of healthy controls). Furthermore, since complex cognitive impairment is associated with multi-domain impairment, less traumatic brain injury patients are divided into three subgroups by counting cognitive domain impairment in less traumatic brain injury patients, depending on the number of areas of cognitive impairment. For each patient, the following scoring criteria were used: the damage without cognitive domain is used as the damage without cognitive domain, one and only one cognitive domain is used as the damage with single cognitive domain, and two or more cognitive domain is used as the damage with multiple cognitive domains, so that whether the patient has cognitive disorder is distinguished.

4. Statistical comparison of dynamic indexes of patients with mild cerebral trauma in different cognitive states in S4, thereby verifying accuracy of the model

The model was considered reliable if there was a significant difference in NII values between subgroups using a one-way anova with the correlation of NII values to the neuropsychological scale.

In one embodiment, the invention provides a system for identifying cognitive level of a patient with mild brain trauma, which can be used for realizing the method for identifying cognitive level of a patient with mild brain trauma, and in particular, the system for identifying cognitive level of a patient with mild brain trauma comprises an extraction module and an identification module.

The extraction module is used for extracting time sequence signals in the ternary network and carrying out dynamic analysis; constructing a dynamic brain pattern model according to the dynamic analysis result, and extracting dynamic indexes from the dynamic brain pattern model; the identification module is used for grouping the cognitive level of the mild brain trauma patient according to the cognitive scale of the mild brain trauma patient and the extracted dynamic index, and identifying the cognitive level of the mild brain trauma patient.

In yet another embodiment of the present invention, a terminal device is provided, the terminal device including a processor and a memory, the memory for storing a computer program, the computer program including program instructions, the processor for executing the program instructions stored by the computer storage medium. The processor may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processor, digital signal processor (Digital Signal Processor, DSP), application specific integrated circuit (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, etc., which are the computational core and control core of the terminal adapted to implement one or more instructions, in particular to load and execute one or more instructions to implement the corresponding method flow or corresponding functions; the processor of an embodiment of the present invention may be used to identify the operation of a method of cognitive level in a patient with mild brain trauma, comprising:

Extracting time sequence signals in a ternary network and carrying out dynamic analysis; constructing a dynamic brain pattern model according to the dynamic analysis result, and extracting dynamic indexes from the dynamic brain pattern model; the cognitive level of the patient with mild brain trauma is identified by grouping the cognitive level of the patient with mild brain trauma according to the cognitive scale of the patient with mild brain trauma and the extracted dynamic index.

In a further embodiment of the present invention, the present invention also provides a storage medium, in particular, a computer readable storage medium (Memory), which is a Memory device in a terminal device, for storing programs and data. It will be appreciated that the computer readable storage medium herein may include both a built-in storage medium in the terminal device and an extended storage medium supported by the terminal device. The computer-readable storage medium provides a storage space storing an operating system of the terminal. Also stored in the memory space are one or more instructions, which may be one or more computer programs (including program code), adapted to be loaded and executed by the processor. The computer readable storage medium may be a high-speed RAM Memory or a Non-Volatile Memory (Non-Volatile Memory), such as at least one magnetic disk Memory.

One or more instructions stored in a computer-readable storage medium may be loaded and executed by a processor to implement the respective steps of the method of identifying a cognitive level in a patient with mild brain trauma in the above-described embodiments; one or more instructions in a computer-readable storage medium are loaded by a processor and perform the steps of:

Fig. 2 is a schematic diagram of a computer device according to an embodiment of the present invention. As shown in fig. 2, the computer device 60 of this embodiment includes: a processor 61, a memory 62 and a computer program 63 stored in the memory 62 and executable on the processor 61, which computer program 63 when executed by the processor 61 implements the method of identifying cognitive levels in patients with mild brain trauma in an embodiment, which is not described in detail herein for avoiding repetition. Alternatively, the computer program 63, when executed by the processor 61, performs the functions of the various models/units in the system for identifying cognitive levels in patients with mild brain trauma, which are not described in detail herein to avoid repetition.

The computer device 60 may be a desktop computer, a notebook computer, a palm top computer, a cloud server, or the like. Computer device 60 may include, but is not limited to, a processor 61, a memory 62. It will be appreciated by those skilled in the art that fig. 2 is merely an example of a computer device 60 and is not intended to limit the computer device 60, and may include more or fewer components than shown, or may combine certain components, or different components, e.g., a computer device may also include an input-output device, a network access device, a bus, etc.

The processor 61 may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The memory 62 may be an internal storage unit of the computer device 60, such as a hard disk or memory of the computer device 60. The memory 62 may also be an external storage device of the computer device 60, such as a plug-in hard disk provided on the computer device 60, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), or the like.

Further, the memory 62 may also include both internal storage units and external storage devices of the computer device 60. The memory 62 is used to store computer programs and other programs and data required by the computer device. The memory 62 may also be used to temporarily store data that has been output or is to be output.

For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. The components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.

1. Acquisition of resting state functional magnetic resonance imaging data and structural data for patients with mild brain trauma

The selection of the group of mild brain trauma patients tested was performed during the period of 8 months 2016 to 5 months 2018, with 109 consecutive ill head trauma patients recruited from the local emergency department as the initial population. The inclusion and exclusion of patients with mild brain trauma were done according to the criteria set by the world health organization's neurotrauma working group.

Written informed consent for each participant had been obtained prior to the start of the experimental procedure. The research program has been approved by the ethical committee of the national institute of science and technology of the university of traffic, and accords with the declaration of helsinki.

MRI scans were performed at 3.0T field strength using MRI scanner GE 750 with a 32 channel head coil for all participants. And acquiring resting-state fMRI data by adopting a gradient echo planar imaging sequence, wherein 180 time points are acquired in total, and the first 5 time points in the original fMRI data are removed and the rest 175 time points are reserved because the magnetic field does not reach a steady state just before scanning is started. The total brain layer number 54 is covered and the scan parameters are as follows: repetition time = 2500ms; echo time = 30ms; layer thickness = 3mm; flip angle = 90 °; field of view (FOV) =216 mm×216mm; matrix size = 64 x 64; voxel size = 3mm x 3mm; acquisition time = 7.5min. During the scan, all participants were instructed to relax, close the eyes, remain awake, and do as little as possible to take specific thought.

2. Construction of dynamic brain pattern model

1) And (3) preprocessing the data acquired in the step one.

2) Independent component analysis is performed on the pre-processed data to identify large-scale networks in the pooled population.

First, two-step principal component analysis is adopted to reduce the dimension of the data preprocessed in the step 2), and when the number of ICs is set to 20, the GIFT automatically sets the number of principal components of the first-step PCA to 30.GIFT first performs principal component analysis on fMRI data of each patient with mild brain trauma at individual level, reduces the dimension to 30 dimensions, then performs a second step of PCA dimension reduction on all the data tested at group level, and reduces the collected data to 20 components. The first step of individual level PCA can project data onto a main feature subspace and preliminarily dimension-reduce the data; group level PCA can then further reduce the dimensionality of the data to the set number of ICs. To derive 20 independent components that are stable and reliable, the GIFT software makes ICs estimates by repeating the Infomax algorithm 10 times on the gca analysis algorithm ICASSO to identify the most stable and reliable components. Next, using a time-space double regression inversion reconstruction method, the spatial distribution and time series of 20 ICs tested for the mild brain trauma patient were obtained, and the spatial distribution of each individual component tested for each mild brain trauma patient was converted to a z-score (subtracting the mean value, divided by the standard deviation). After obtaining 20 ICs with GIFT, all spatial maps tested for each ICs were subjected to a random effect single sample t-test, where a threshold of |t| >10 was set to further select voxels of the ICs, in order to increase the representativeness of the ICs. All ICs were evaluated from the group ICs graph that the network exhibited peak activation of gray matter, the time course was dominated by low frequency fluctuations (based on frequency analysis of the estimated ICs spectrum) and showed low spatial overlap with known white matter structures, blood vessels, ventricles, motion and susceptibility artifacts. Finally, as shown in fig. 3, 5 components SN, left CEN, right CEN, front DMN, and rear DMN corresponding to the three network model described previously were determined according to a widely used visual inspection procedure.

3) And extracting time sequence signals from the ternary network and carrying out dynamic analysis.

And determining the spatial distribution of the ternary network in the brain by using independent component analysis, and extracting the fMRI time sequence of all patients with mild cerebral trauma tested on the ternary network. As shown in fig. 4, to study the time-varying cross-network interactions of the ternary network, a sliding window dynamic function connection method is used to dynamically change the data. First, the window width is set to w and the step length is set to s. Units: TR. A sliding window length of 50TR and a step shift of 1TR are selected. For each patient with mild brain trauma, a total of 126 windows were generated in this step. In each sliding window, the average time series of 5 brain networks are extracted and the Pearson correlation coefficient between each pair of average time series of the 5 networks is calculated. Then a 5 x 5 correlation matrix is obtained, and a fisher-to-z transformation is performed on all the correlation matrices to improve the normalization of the correlation distribution.

4) And extracting dynamic function indexes.

Considering the core role of SN in generating causal control signals that initiate dynamic switching between CEN and DMN, NII is measured to estimate network interactions in each dynamic sliding window. The advantage of NII is that interactions between three networks can be captured simultaneously. The NII is calculated as the poor correlation between SN and CEN time series, and the poor correlation between SN and DMN. The rationale here is that SN and CEN are typically co-activated in a cognition demanding task, while SN and DMN are typically inversely related. Thus, the NII obtains the extent to which SN can temporarily bind to CEN and separate from DMN. In the study, the NII value for each sliding window and the average NII value for each subject were obtained. In general, in the ternary network model, the greater the NII value, the more isolated the network interaction between the SN-CEN and SN-DMN systems. The specific calculation formula is as follows:

NII＝f(CC _SN,CEM )-f(CC _SN,DMN )

Wherein the method comprises the steps of

Here, CC is the Pearson correlation between two component network time series, e.g. CC _SN,CEN Is the correlation between the time series of SN and CEN. f (CC) computes a Fisher-z transform of the Pearson correlation between the two component network time series. Thus, for example, f (CC _SN,CEN ) The Fisher-z transform of the Pearson correlation between the time series of SN and CEN is calculated. For double sided CEN, f (CC _SN,lCEN ) And f (CC) _SN,rCEN ) Then take the average value as f (CC _SN,CEN ). Pair f (CC) _SN,DMN ) The same procedure was also performed.

3. Assessment of cognitive level in patients with mild brain trauma

To quantify the cognitive scores, neuropsychological reports and test data are consulted to assess the extent of injury to each patient in different cognitive domains. The status of each patient is divided into four aspects: cognitive flexibility, executive function, working memory, and linguistic ability. For each cognitive domain, the following scoring table is used: no damage, i.e. no significant damage (defined as mean < 1.5SDs with healthy control group); impaired, meaning reduced cognitive ability (defined as >1.5SDs compared to the average value of healthy control). Thus, patients with mild traumatic brain injury are divided into three subgroups according to the various areas of cognitive impairment. For each patient, the following scoring criteria were used: mild brain trauma without cognitive impairment (no cognitive domain injury), mild brain trauma with mild cognitive impairment (single cognitive domain injury), mild brain trauma with severe cognitive impairment (multiple cognitive domain injury).

4. Comparing differences between groups of NII values at different cognitive levels

In this study, a total of 109 patients with mild brain trauma were included, and the patients were divided into three different subgroups according to the degree of cognitive domain injury, with 68 patients with mild brain trauma and no cognitive impairment (no cognitive domain injury), 26 patients with mild brain trauma and mild cognitive impairment (single cognitive domain injury), and 15 patients with mild brain trauma and severe cognitive impairment (multiple cognitive domain injury). As shown in FIG. 5, the correlation of NII values with the neuropsychological scale was explored using the SPARAN correlation. To illustrate, changes in NII values are related to cognitive changes in the patient. Further, as shown in fig. 6, the one-way anova shows that the NII value of the multi-cognitive domain injury patient group is significantly higher than that of the non-cognitive domain injury patient group (p=0.011), and the NII value of the single-cognitive domain injury patient group is greater than that of the non-cognitive domain injury patient group and less than that of the multi-cognitive domain injury patient group.

In summary, according to the method, the system, the equipment and the medium for identifying the cognitive level of the patient with mild cerebral trauma, the time series of the resting state functional magnetic resonance imaging data of all the patients with mild cerebral trauma are extracted from the ternary network, and the extracted time series are dynamically analyzed to obtain dynamic indexes so as to estimate network interaction in each dynamic sliding window. The three-way network is connected with the cognition of the mild brain trauma by means of the dynamic index, a dynamic model for distinguishing the cognition state of the mild brain trauma patient is constructed by calculating the obvious difference of the dynamic index values of the mild brain trauma patient in different cognition states, the cognition level of the mild brain trauma patient is identified, the cognition level of the mild brain trauma patient is helped to be clinically and further identified, and an effective auxiliary detection means is provided for early identification of the cognition problem of the mild brain trauma.

It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions. The functional units and modules in the embodiment may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit, where the integrated units may be implemented in a form of hardware or a form of a software functional unit. In addition, the specific names of the functional units and modules are only for distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working process of the units and modules in the above system may refer to the corresponding process in the foregoing method embodiment, which is not described herein again.

In the foregoing embodiments, the descriptions of the embodiments are emphasized, and in part, not described or illustrated in any particular embodiment, reference is made to the related descriptions of other embodiments.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

In the embodiments provided in the present invention, it should be understood that the disclosed apparatus/terminal and method may be implemented in other manners. For example, the apparatus/terminal embodiments described above are merely illustrative, e.g., the division of the modules or units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection via interfaces, devices or units, which may be in electrical, mechanical or other forms.

The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.

The integrated modules/units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the present invention may implement all or part of the flow of the method of the above embodiment, or may be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, and when the computer program is executed by a processor, the computer program may implement the steps of each of the method embodiments described above. Wherein the computer program comprises computer program code which may be in source code form, object code form, executable file or some intermediate form etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (RandomAccess Memory, RAM), an electrical carrier wave signal, a telecommunications signal, a software distribution medium, etc., it should be noted that the computer readable medium may contain content that is appropriately increased or decreased according to the requirements of jurisdictions and patent practices, such as in certain jurisdictions, according to the jurisdictions and patent practices, the computer readable medium does not contain electrical carrier wave signals and telecommunications signals.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

Finally, it should be noted that: the above embodiments are only for illustrating the technical aspects of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the above embodiments, it should be understood by those of ordinary skill in the art that: modifications and equivalents may be made to the specific embodiments of the invention without departing from the spirit and scope of the invention, which is intended to be covered by the claims.

Claims

1. A method for identifying cognitive level in a patient with mild brain trauma, characterized by extracting time-series signals in a ternary network and performing dynamic analysis; constructing a dynamic brain pattern model according to the dynamic analysis result, and extracting dynamic indexes from the dynamic brain pattern model; the cognitive level of the patient with mild brain trauma is identified by grouping the cognitive level of the patient with mild brain trauma according to the cognitive scale of the patient with mild brain trauma and the extracted dynamic index.

2. A method of identifying cognitive levels in a patient with mild brain trauma as claimed in claim 1, wherein the ternary network is obtained from resting functional magnetic resonance imaging data of the patient with mild brain trauma by independent component analysis.

3. A method of identifying cognitive levels in a patient with mild brain trauma as claimed in claim 2, wherein the step of independent component analysis is: the method comprises the steps of performing dimension reduction on resting state functional magnetic resonance imaging data of a patient with mild cerebral trauma by using two principal component analysis, using an Infomax algorithm, performing inversion reconstruction, obtaining the time histories and the space diagrams of the ICs tested by all the patient with mild cerebral trauma, converting the time histories and the space diagrams into z scores, and then selecting 5 ICs from the time histories and the space diagrams, wherein the 5 ICs correspond to a front default mode network, a rear default mode network, a left central execution network, a right central execution network and SN respectively;

4. A method of identifying cognitive levels in a patient with mild brain trauma according to any one of claims 1 to 3, wherein pearson correlation coefficients are obtained for each brain segment of the patient with mild brain trauma by dynamic analysis, and dynamic indexes are calculated from the pearson correlation coefficients.

5. A method of identifying a cognitive level in a patient with mild brain trauma according to any one of claims 1 to 3, characterised in that the cognitive scale of the patient with mild brain trauma is obtained using neuropsychological measurements; in the neuropsychological measurement method, the state of each patient with mild cerebral trauma is divided into four cognitive domains, namely cognitive flexibility, executive function, working memory and language ability, the cognitive flexibility is measured by using a digital symbol coding score and a test A part of WAIS-III, the executive function is estimated by using a forward digital span of WAIS-III, the working memory is estimated by using a backward digital span of WAIS-III, and the language ability and the semantic memory are checked by using a language fluency test.

6. The method of claim 5, wherein the evaluation criteria for grouping is: for each cognitive domain, an average value of < 1.5SDs compared with the healthy control group is taken as no damage, and an average value of more than or equal to 1.5SDs compared with the healthy control group is taken as damage.

7. The method of claim 6, wherein for a lesion, no cognitive domain injury is taken as no cognitive domain injury, one cognitive domain injury is taken as a single cognitive domain injury, and two or more cognitive domain injuries are taken as multiple cognitive domain injuries.

8. A system for identifying cognitive levels in a patient with mild brain trauma, comprising:

9. A computer readable storage medium storing one or more programs, wherein the one or more programs comprise instructions, which when executed by a computing device, cause the computing device to perform any of the methods of claims 1-7.

10. A computing device, comprising: one or more processors, memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs comprising instructions for performing any of the methods of claims 1-7.