Nuclear magnetic resonance diagnosis system for social cognition and cholinergic pathway loss after stroke

Through the nuclear magnetic resonance diagnosis system of social cognition and cholinergic pathway disconnection after stroke, combined with multimodal MRI technology and deep learning, the problem of difficult-to-understand relationship between social cognitive dysfunction and cholinergic pathway after stroke is solved, and the problem of difficult-to-understand relationship between social cognitive dysfunction and cholinergic pathway after stroke is achieved. Understanding CCP network connectivity status and social dysfunction prediction in stroke patients promotes disease intervention and rehabilitation processes.

CN118986320AInactive Publication Date: 2024-11-22DONGGUAN PEOPLES HOSPITAL
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411106023.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-13
Publication Date
2024-11-22
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

Although the patient's physical function is restored after stroke, there is still a low degree of social life participation. It is mainly due to social cognitive dysfunction. It is difficult for the existing technology to fully understand the relationship between social cognitive function and cholinergic pathway after stroke. Impacts disease prognosis assessment and recovery process.

Method used

A nuclear magnetic resonance diagnosis system for the loss of social cognition and cholinergic pathway after stroke was developed, including image acquisition module, social cognitive evaluation module, CCP network establishment module and brain network evaluation module, through multimodal MRI technology and Deep learning, establish a social dysfunction prediction model, and understand the patient's CCP network connection status and the inherent laws of social cognitive dysfunction.

Benefits of technology

This system can analyze the social cognitive function and brain network connection status of stroke patients in multiple dimensions, explore the evolution and recovery process of social cognitive impairment after stroke, help to conduct early disease intervention, and improve the evaluation of prognosis of patients with ischemic stroke patients and therapeutic effects.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118986320A_ABST
    Figure CN118986320A_ABST
Patent Text Reader

Abstract

The invention discloses a nuclear magnetic resonance diagnosis system for post-stroke social cognition and cholinergic pathway loss in the technical field of post-stroke cognitive impairment diagnosis. The nuclear magnetic resonance diagnosis system comprises an image acquisition module, a social cognition evaluation module, a CCP network establishment module and a brain network evaluation learning module. The CCP network establishment module establishes a brain network based on the MRI examination image acquired by the image acquisition module, and establishes a CCP network based on Ach distribution; the brain network evaluation learning module corresponds social cognition function evaluation data to a CCP network, and performs deep learning based on the obtained macroscopic brain structure atrophy, a focus area related to social cognition, CCP network cortex-subcortex structural connection injury and rs-fMRI brain function analysis key parameters to obtain a social dysfunction prediction model; therefore, the condition of the social cognitive impairment after the ischemic stroke can be known, the CCP network connection condition of the patient and the internal law of the social cognitive impairment after the acute ischemic stroke can be preliminarily known, and disease intervention can be carried out as soon as possible.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of diagnosis of cognitive impairment after stroke, and specifically relates to a nuclear magnetic resonance diagnosis system for post-stroke social cognition and cholinergic pathway disconnection. Background Art

[0002] According to the WHO classification of function, disability and health, the prognosis of a disease needs to be judged from three different aspects, including: physical dysfunction, limited daily activities and reduced social participation. Studies have found that some stroke patients whose physical functions have basically recovered and who have no obvious cognitive impairment still have low participation in social life.

[0003] Having good social skills is the basis of social behavior and interpersonal communication; social cognitive dysfunction after stroke is believed to impair the patient's social skills and reduce social participation. In order to more comprehensively analyze the prognosis of stroke patients, it is necessary to evaluate the patient's social cognitive function.

[0004] Among them, social cognition refers to the psychological processes involved in perceiving, encoding, storing, retrieving and regulating information about others and oneself. These processes include perceiving social cues, sharing experiences, inferring other people's thoughts and emotions, and managing emotional responses to others.

[0005] If social cognitive impairment occurs, such as the inability to perceive, understand, and fully respond to social cues, it will lead to a decrease in social participation, a decrease in daily living ability, and a decrease in life satisfaction. Therefore, using social cognitive function as a prognosis of stroke can more comprehensively reflect the comprehensive impact of stroke and is of great value for the rehabilitation of social function.

[0006] In the existing technology, acetylcholine (ACh), as an excitatory neuromodulator of the cerebral cortex, is involved in almost all aspects of cortical function, and its reduction is closely related to the occurrence of cognitive dysfunction. With the rapid development of multimodal magnetic resonance imaging technology, unified spatial registration analysis of MRI image results of different modalities can provide a more dimensional, comprehensive and in-depth understanding of the relationship between social cognitive function and CCP (cerebral cortical cholinergic pathway) in stroke patients. Summary of the invention

[0007] The purpose of the present invention is to provide a nuclear magnetic resonance diagnosis system for post-stroke social cognition and cholinergic pathway disconnection, to understand the situation of social cognitive dysfunction after ischemic stroke, to preliminarily understand the patient's CCP network connection status and the inherent laws of social cognitive dysfunction after acute ischemic stroke, and to help early disease intervention.

[0008] In order to achieve the above object, the technical solution of the present invention is as follows:

[0009] The MRI diagnostic system for post-stroke social cognition and cholinergic pathway disconnection includes an image acquisition module, a social cognition evaluation module, a CCP network establishment module, and a brain network evaluation learning module;

[0010] The image acquisition module is used to acquire the patient's MRI examination image and send the MRI examination image to the CCP network establishment module;

[0011] The social cognition evaluation module is used to obtain the patient's social cognition function evaluation data and send the social cognition function evaluation data to the CCP network establishment module;

[0012] The CCP network establishment module is used to establish a brain network based on MRI examination images, and mark the Ach distribution into the brain network to establish a CCP network;

[0013] The brain network assessment module is used to match the social cognitive function assessment data with the CCP network, obtain macroscopic brain structure atrophy, lesion areas related to social cognition, CCP network cortical-subcortical structural connection damage and rs-fMRI brain function analysis key parameters, substitute the key parameters into the neural network learning module for deep learning, and obtain a social dysfunction prediction model.

[0014] Furthermore, social cognitive function assessment data were evaluated based on theory of mind, emotion cognition, and empathy.

[0015] Furthermore, MRI examination images include 3D-T1W, DWI, DTI, T2-FLAIR and rs-fMRI.

[0016] Furthermore, 3D-T1W is used to calculate brain structure capacity and brain structure atrophy in the brain network; DWI is used to segment the infarct area in the brain network; DTI is used to establish the cortical mapping of CCP fiber connection density in the brain network; T2-FLAIRT2 is used to segment white matter highlight areas; rs-fMRI is used to calculate brain functional network connectivity.

[0017] Furthermore, the macroscopic brain structural atrophy was analyzed by using the quantitative tool AccuBrain to segment the 3D-T1W brain structure and calculate the brain structure volume and atrophy degree of the corresponding brain network for each patient.

[0018] Furthermore, the method for extracting lesion areas related to social cognition is as follows: first, segment the infarct area based on DWI images, then segment the white matter highlight area based on T2-FLAIR, and mark the infarct area and the white matter highlight area in the standard space accordingly;

[0019] The VLSM method was used to identify brain regions significantly associated with social cognition as seed feature regions. Each infarct area or white matter highlight area was then used to predict the patient's social cognitive state, and the lesion areas associated with the prediction were screened out.

[0020] Furthermore, the method for extracting cortical-subcortical structural connection damage in the CCP network is as follows: first, the CCP white matter connection pathway is obtained based on 3D-T1W; then the Ach distribution is obtained through DTI, and the data are grouped based on the size of different social cognitive function assessment data, and then the connection between the social cognitive function assessment data and the CCP network is measured according to the FA value and MD value.

[0021] Furthermore, the method of brain function analysis based on rs-fMRI is as follows: first, DMN is established using rs-fMRI, and the brain network is divided into 210 cortices and 36 regions of interest according to Brainnetome Atlas. The regions of interest are correlated with the seed feature regions in the VLSM method, and the differences in brain connection dynamic models between people with progressive disease and people with stable cognitive function are compared to determine the functional brain network change areas that play a predictive role.

[0022] Furthermore, when the CCP white matter connection pathway is obtained based on 3D-T1W, the CCP white matter connection pathway is semi-quantitatively evaluated by using the cholinergic pathway high signal scale.

[0023] Furthermore, FA values ​​were obtained using a supervoxel-based statistical method, and MD values ​​were obtained using a nerve fiber tracking algorithm and a network analysis based on graph theory.

[0024] The following beneficial effects were achieved by adopting the above scheme: (1) The present invention explores the neural mechanism of the occurrence and development of social cognitive dysfunction after stroke and studies its relationship with the network connection of cholinergic pathways in the cerebral cortex, which is expected to further understand the evolution and rehabilitation process of social cognitive dysfunction after stroke.

[0025] (2) The application of multimodal MRI technology, including various sMRI images and DTI that can observe the CCP white matter connection pathways, and fMRI that can analyze brain networks, can provide a multi-dimensional understanding of the stroke lesion area and CCP network connectivity in stroke patients through comprehensive analysis. In addition to understanding the relationship between the stroke area and social cognition, it can also explore the inherent laws between the CCP network connectivity and the social cognitive function of ischemic stroke patients.

[0026] (3) The present invention can understand the situation of social cognitive dysfunction after ischemic stroke, preliminarily understand the intrinsic law of CCP network connection status and social cognitive dysfunction after acute ischemic stroke, and help to intervene in the disease early. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 Schematic diagram of a nuclear magnetic resonance diagnosis system for post-stroke social cognition and cholinergic pathway disconnection according to an embodiment of the present invention.

[0028] Figure 2 This is a schematic diagram of the quantitative segmentation results of brain regions by the quantitative tool AccuBrain according to an embodiment of the present invention.

[0029] Figure 3 This is a flow chart of a method for jointly analyzing symptom correlations of multiple injuries according to an embodiment of the present invention. DETAILED DESCRIPTION

[0030] The following is further described in detail through specific implementation methods:

[0031] The embodiment is basically as shown in the attached Figures 1 to 3 As shown: a nuclear magnetic resonance diagnosis system for post-stroke social cognition and cholinergic pathway disconnection, including an image acquisition module, a social cognition evaluation module, a CCP network establishment module and a brain network evaluation learning module, wherein the image acquisition module is used to acquire the patient's MRI examination image and send the MRI examination image to the CCP network establishment module; wherein the MRI examination image includes 3D-T1W (three-dimensional T1 weighted image), DWI (diffusion weighted image), DTI (diffusion tensor imaging), T2-FLAIRT2 (weighted fluid attenuated inversion recovery image) and rs-fMRI (resting state functional MRI image), and 3D-T1W is used to calculate the quantitative parameters of brain structure volume and brain structure atrophy; DWI is used to segment the infarct area; DTI is used to establish a white matter fiber connection density cortical mapping map; T2-FLAIRT2 is used to segment the white matter highlight area (WMH); rs-fMRI is used to calculate the brain functional network connection.

[0032] The social cognition evaluation module is used to obtain the patient's social cognitive function evaluation data and send the social cognitive function evaluation data to the CCP network establishment module; wherein the social cognitive function evaluation data is evaluated based on theory of mind, emotional cognition and empathy.

[0033] Theory of mind was assessed using the Cartoon Test, in which patients describe 12 cartoons of humorous situations. Half of the pictures simply required the subject to describe the attributes of the cartoonist's mental state to understand the humorous situation, while the other half required the subject to understand the meaning of the picture, which was based on the patient's belief understanding of the cartoon character. The total score on the Cartoon Test ranged from 0 to 36, with higher scores indicating better theory of mind.

[0034] Emotional recognition was assessed using the Ekman 60-Faces test, in which patients were asked to identify 60 faces, each showing 10 basic emotions: fear, disgust, anger, happiness, sadness, or surprise. Each face was identified for 3 seconds. The total score ranged from 0 to 60, with higher scores reflecting better emotion recognition ability.

[0035] Empathy was assessed using the Faux Pas test, in which patients were asked to measure their feelings for victims of failed fertility tests. Patients rated their answers to the 10 items on a scale from 0 to 5, with higher scores indicating more empathy.

[0036] For example, the degree of CCP damage is closely related to the prognosis of stroke. Acute ischemic stroke lesions can cause CCP damage in patients, and the severity of the damage is related to poor prognosis within 6 months after stroke. And CCP damage is also highly correlated with new cognitive dysfunction within 3 months after stroke. Since the prefrontal cortex is an important component of CCP, British scholar Jackie Hamilton and others found that patients with infarction in this area had impaired mental abilities and executive dysfunction. Scholar YanFan and others found that damage to the anterior horn of the insula can lead to a decrease in empathy. These research results suggest that CCP damage is associated with social cognitive impairment after stroke.

[0037] The CCP network establishment module is used to establish a brain network based on MRI examination images, and mark the Ach distribution into the brain network to establish a CCP network.

[0038] For example, acetylcholine (ACh), as an excitatory neuromodulator of the cerebral cortex, is involved in almost all aspects of cortical function, and its reduction is closely related to the occurrence of cognitive dysfunction. ACh is mainly located in the axons of cholinergic neurons and is synthesized by choline and acetyl coenzyme α under the action of Ach transferase (choline acetyltransferase, ChAT). There are two types of AcH receptors: muscarinic Ach receptors (mAChRs) and nicotinic Ach receptors (nAChRs), which are located in the presynaptic and postsynaptic membranes of the brain, respectively, and play an important role in regulating the release of neurotransmitters related to cognitive function, such as glutamate, γ-aminobutyric acid, dopamine, and norepinephrine. ChAT is the most specific marker of cholinergic neurons. The cortical cholinergic pathway (CCP) was discovered by immunohistochemical staining of ChAT and magnetic resonance imaging superposition analysis technology. CCP is an important component of the brain network connection structure. CCP includes projection fibers from neurons in tissues such as the Meynert basal nucleus, Broca diagonal band, and medial septal nucleus, connecting the bilateral frontal lobes, bilateral temporal lobes, genu and splenium of the corpus callosum, parietal-occipital region, cingulate bundle, and amygdala, forming a complex neural network pathway. These structures cooperate with each other to participate in the regulation of complex brain functions including cognitive processes, so the degree of CCP damage is closely related to the prognosis of stroke.

[0039] The brain network assessment module is used to match the social cognitive function assessment data with the CCP network, obtain macroscopic brain structure atrophy, lesion areas related to social cognition, CCP network cortical-subcortical structural connection damage and rs-fMRI brain function analysis key parameters, substitute the key parameters into the neural network learning module for deep learning, and obtain a social dysfunction prediction model.

[0040] For example, the macroscopic brain structural atrophy uses the quantitative tool AccuBrain to perform brain structural segmentation on 3D-T1W and calculate the brain structural volume and atrophy degree of the corresponding brain network of each patient, such as Figure 2 shown.

[0041] The method for extracting lesion areas related to social cognition is as follows: first, segment the infarct area based on DWI images, and then segment the white matter highlight area based on T2-FLAIR, and mark the infarct area and white matter highlight area accordingly in the standard space; use the VLSM method to determine the brain area significantly related to social cognition as the seed feature area, and then predict the patient's social cognitive status for each infarct area or white matter highlight area, and screen out the lesion areas that are associated with the prediction.

[0042] Since the VLSM method is a fully automatic and hypothesis-free analysis method, it can establish a point-by-point connection between the spatial location of lesions in the brain and symptoms or behavioral data, and is of great value for the study of the distribution of lesions in groups of functional defects (such as language and motor defects, such as aphasia or motor dysfunction). In this embodiment, the infarct area is segmented from the DWI image using a deep learning method, and the white matter highlight area (related to post-stroke social cognition) is segmented from the T2-FLAIR, and the lesions on different modalities are unified into a standard space through spatial registration. In the standard space, the social cognitive status of the patient is predicted based on the lesion volume of each brain region or the lesion status (normal / damaged) based on the voxel, and the lesion area that contributes significantly to the prediction is screened out, as shown in the following example. Figure 3 shown.

[0043] The method for extracting cortical-subcortical structural connection damage in the CCP network is as follows: first, when obtaining the CCP white matter connection pathway based on 3D-T1W, the CCP white matter connection pathway is semi-quantitatively evaluated by using the cholinergic pathway high signal scale; then, the Ach distribution is obtained through DTI, and the data are grouped based on the size of different social cognitive function assessment data, and then the connection between the social cognitive function assessment data and the CCP network is measured according to the FA value (anisotropy value) and MD value (mean diffusion rate).

[0044] Among them, when obtaining the CCP white matter connection pathway based on 3D-T1W, the CCP white matter connection pathway will also be semi-quantitatively evaluated by using the cholinergic pathway high signal scale.

[0045] Based on the neural fiber tracking algorithm and the network analysis based on graph theory, DTI can calculate a series of brain structure network connectomics parameters; while brain network functional connectomics parameters can be generated through the time correlation analysis of resting-state functional magnetic resonance imaging. From DTI, parameters such as fractional anisotrophy (FA) and mean difusivity (MD) that reflect the state of brain structure connection can be calculated. The cross-modal joint parameter statistical analysis based on multimodal brain networkomics will provide a rich description of brain functional state and become an important indicator for exploring the structural and functional integrity of CCP.

[0046] At the same time, a new super-voxel-based statistical analysis method is based on graph clustering super-voxel segmentation to divide the white matter tensor into diffuse uniform super-voxels, which can effectively improve the recognition error. This method divides the white matter tensor into diffuse uniform super-voxels based on graph clustering super-voxel segmentation, and further conducts in-depth quantitative analysis of brain white matter fibers in DTI. In the comparison of DTI data of people with progressive disease and people with stable cognitive function, the anisotropy (FA) value is analyzed to identify fibers with significant statistical differences.

[0047] The method of brain function analysis based on rs-fMRI is as follows: first, rs-fMRI is used to establish the DMN (default state network), and the brain network is divided into 210 cortices and 36 regions of interest according to the Brainnetome Atlas. The regions of interest are correlated with the seed feature regions in the VLSM method, and the differences in the dynamic models of brain connections between people with progressive disease and people with stable cognitive function are compared to identify the predictive ChAT as the functional brain network change area.

[0048] To further examine the effect of a single CCP structure on cognitive dysfunction, a multiple linear regression model was used to explore the effect of CCP structure on social cognitive dysfunction by correcting for age, education level, cognitive function, anxiety level, and depression level.

[0049] At the same time, cerebral infarction volume and gray matter volume will be the main analysis indicators of sMRI. The quantitative measurement tool AccuBrain can provide parameters such as the volume of the whole brain and each major lobe. The t-test was used to compare the differences in cerebral infarction volume, whole brain volume, brain atrophy and the volume of each major lobe between the groups. The linear regression equation model was used to explore the effects of whole brain volume, lobe volume and cerebral infarction volume on social cognitive dysfunction, so as to understand the situation of social cognitive dysfunction after ischemic stroke, and preliminarily understand the intrinsic laws of the patient's CCP network connectivity and social cognitive dysfunction after acute ischemic stroke, which is helpful for early disease intervention.

[0050] The above is only an embodiment of the present invention, and the common knowledge such as the known specific structure and / or characteristics in the scheme is not described in detail here. It should be pointed out that for those skilled in the art, several deformations and improvements can be made without departing from the structure of the present invention, which should also be regarded as the protection scope of the present invention, and these will not affect the effect of the implementation of the present invention and the practicality of the patent. The scope of protection required by this application shall be based on the content of its claims, and the specific implementation methods and other records in the specification can be used to interpret the content of the claims.

Claims

1. An MRI diagnostic system for post-stroke social cognition and cholinergic pathway disconnection, characterized by: It includes image acquisition module, social cognition assessment module, CCP network establishment module and brain network assessment learning module; The image acquisition module is used to acquire the patient's MRI examination image and send the MRI examination image to the CCP network establishment module; The social cognition evaluation module is used to obtain the patient's social cognition function evaluation data and send the social cognition function evaluation data to the CCP network establishment module; The CCP network establishment module is used to establish a brain network based on MRI examination images, and mark the Ach distribution into the brain network to establish a CCP network; The brain network assessment module is used to match the social cognitive function assessment data with the CCP network, obtain macroscopic brain structure atrophy, lesion areas related to social cognition, CCP network cortical-subcortical structural connection damage and rs-fMRI brain function analysis key parameters, substitute the key parameters into the neural network learning module for deep learning, and obtain a social dysfunction prediction model.

2. The magnetic resonance imaging system for post-stroke social cognition and cholinergic pathway disconnection according to claim 1, characterized in that: Social cognitive function assessment data were assessed based on theory of mind, emotion cognition, and empathy.

3. The magnetic resonance imaging system for post-stroke social cognition and cholinergic pathway disconnection according to claim 2, characterized in that: MRI examination images include 3D-T1W, DWI, DTI, T2-FLAIR and rs-fMRI.

4. The magnetic resonance imaging system for post-stroke social cognition and cholinergic pathway disconnection according to claim 3, characterized in that: 3D-T1W is used to calculate brain structure capacity and brain structure atrophy in the brain network; DWI is used to segment the infarct area in the brain network; DTI is used to establish the cortical mapping of CCP fiber connection density in the brain network; T2-FLAIRT2 is used to segment white matter highlight areas; rs-fMRI is used to calculate brain functional network connectivity.

5. The magnetic resonance imaging system for post-stroke social cognition and cholinergic pathway disconnection according to claim 4, characterized in that: Macroscopic brain structural atrophy The quantitative tool AccuBrain was used to segment the brain structure of 3D-T1W and calculate the brain structure volume and atrophy degree of the corresponding brain network for each patient.

6. The magnetic resonance imaging system for post-stroke social cognition and cholinergic pathway disconnection according to claim 5, characterized in that: The method for extracting lesion areas related to social cognition is as follows: first, segment the infarct area based on DWI images, then segment the white matter highlight area based on T2-FLAIR, and mark the infarct area and white matter highlight area in the standard space; The VLSM method was used to identify brain regions significantly associated with social cognition as seed feature regions. Each infarct area or white matter highlight area was then used to predict the patient's social cognitive state, and the lesion areas associated with the prediction were screened out.

7. The magnetic resonance imaging system for post-stroke social cognition and cholinergic pathway disconnection according to claim 6, characterized in that: The method for extracting cortical-subcortical structural connection damage in the CCP network is as follows: first, the CCP white matter connection pathway is obtained based on 3D-T1W; then the Ach distribution is obtained through DTI, and the data are grouped based on the size of different social cognitive function assessment data, and then the connection between the social cognitive function assessment data and the CCP network is measured based on the FA value and MD value.

8. The magnetic resonance imaging system for post-stroke social cognition and cholinergic pathway disconnection according to claim 7, characterized in that: The method of brain function analysis based on rs-fMRI is as follows: first, rs-fMRI is used to establish DMN, and the brain network is divided into 210 cortices and 36 regions of interest according to Brainnetome Atlas. The regions of interest are correlated with the seed feature regions in the VLSM method, and the differences in brain connection dynamic models between people with progressive disease and people with stable cognitive function are compared to determine the functional brain network change areas that play a predictive role.

9. The magnetic resonance imaging system for post-stroke social cognition and cholinergic pathway disconnection according to claim 8, characterized in that: When obtaining the CCP white matter connection pathway based on 3D-T1W, the CCP white matter connection pathway will also be semi-quantitatively evaluated by using the cholinergic pathway high signal scale.

10. The magnetic resonance imaging system for post-stroke social cognition and cholinergic pathway disconnection according to claim 9, characterized in that: FA values ​​were obtained using a supervoxel-based statistical method; MD values ​​were obtained using a nerve fiber tracking algorithm and a network analysis based on graph theory.