56 results about "Functional brain" patented technology

The invention discloses a construction method of a dyskinesia phenotype classification model of a Parkinson's disease patient and a diagnosis system, and belongs to the field of medical auxiliary diagnosis devices. The system comprises an image acquisition module and a phenotype classification module, wherein the classification module is composed of a space-time diagram convolution feature extraction module, a hierarchical node fusion module, a functional brain network construction and feature extraction module, a local brain region feature screening module, a hierarchical brain feature pairing fusion module and an output module. According to the method, multi-modal brain image data are fused, space-time and complex relation characteristics of a brain region are deeply mined, a key lesion brain region is positioned, and dyskinesia phenotypes are accurately classified by training a neural network. The system can significantly improve the diagnosis accuracy of the Parkinson's disease dyskinesia phenotype, has good expansibility and adaptability, and provides a scientific basis for early diagnosis and personalized intervention. The invention further relates to an operation method of the system, an auxiliary diagnosis device and a computer readable storage medium.

The invention relates to the technical field of determination of nerve regulation and control precise stimulation targets, and discloses an individualized multi-frequency regulation and control stimulation system for Rett regulation and control. The individualized multi-frequency regulation and control stimulation system comprises a data acquisition module, a structure and function brain image analysis module and a multi-frequency electroencephalogram self-adaptive regulation and control module, the data acquisition module is used for acquiring resting state functional magnetic resonance imaging data rs-fMRI, structural magnetic resonance imaging data sMRI and EEG data, and the structural and functional brain image analysis module is used for identifying an abnormal brain area of an RTT patient and determining an optimal stimulation target. The multi-frequency electroencephalogram self-adaptive regulation and control module comprises two sub-modules including an electroencephalogram state recognition module and an FUS self-adaptive stimulation module, and the electroencephalogram state recognition module is used for analyzing EEG signals, extracting frequency band power change and instantaneous phase information corresponding to a target brain region and providing real-time feedback signals for self-adaptive regulation and control. According to the system, the target spot is accurately determined, and the individualized accurate stimulation target spot is determined by combining the structure and function image and the disease exposure model.

The embodiment of the invention discloses an autism spectrum disorder subtype division method and device, a medium and a program product. The method comprises the following steps: constructing a connection brain map based on neuroimaging data and a functional brain region division template of an ASD individual; constructing a brain age regression model, predicting the social brain age of the ASD individual based on the connection brain map and the brain age regression model, and obtaining the brain age difference of the ASD individual in combination with the actual brain age of the ASD individual; obtaining an ADOS social score of the ASD individual, and carrying out clustering analysis on the ADOS social score and the brain age difference to obtain a clustering subtype; and carrying out behavioral verification and neural dimension verification on the clustering subtypes, and constructing a combined portrait among the subtypes, the behavior features and the neural features based on a verification result. According to the method, the social brain age can be predicted by constructing the connection brain map, the clustering subtypes are divided, the combined portrait is constructed, a doctor can be accurately assisted to detect ASD subtype neural development differences, and discovery and application of subtype specific biomarkers are assisted.

The invention discloses a visual evoked brain signal decoding method and system based on a multi-modal diffusion model, and the method can reconstruct a high-resolution image from an fMRI signal and generate a descriptive text. According to the method, an fMRI signal is mapped to an image-text detail potential feature space and an image-text advanced semantic feature space of a CLIP model through a lightweight regression model, and an image and a text are generated under the guidance of a joint condition by using a multi-modal diffusion model. According to the method, multi-condition semantic information of image and text features is fused, high-fidelity image and text description are generated from brain signals at the same time by using a multi-mode potential diffusion model for the first time, and the superior ability of functional brain region analysis in the aspect of specific semantic content decoding is revealed. The invention provides a solution for brain-computer interface, neuroscience research and medical auxiliary diagnosis.

A system for estimating a subject's functional brain age using non-invasive electroencephalography (EEG), the system includes: an EEG acquisition module (101) configured to record multichannel EEG signals from the subject; a stimulation control module (102) configured to present a predefined sequence of cognitive and sensory tasks that specifically target the frontal, temporal, parietal and occipital brain regions, and to generate synchronized event markers; a data processing module (103) configured to prepare the recorded EEG signals by filtering, artifact removal, normalization and segmentation into task-oriented time windows; a machine learning module (104) comprising one or more self-monitoring contrastive learning encoders configured to transform the preprocessed EEG signals into latent feature representations; and a brain age estimation module (105) configured to process the latent feature representations to generate a BrainAge Score indicating a difference between a predicted biological brain age and the subject's chronological age.

The invention provides a brain function network causal analysis method based on phase-space reconstruction and unified GCA, and relates to the field of functional brain network analys.The method comprises the steps that fMRI data are collected and preprocessed, and a time sequence of interested nodes is extracted from the preprocessed fMRI data; for extracting time sequences X and Y of any two to-be-analyzed interested nodes, constructing a variable time delay unified Granger causal model based on phase space reconstruction; and traversing all to-be-analyzed node pairs of interest, calculating the causal direction and strength between each pair of nodes to construct a whole-brain directed causal connection matrix, and performing network metric attribute analysis. According to the method, phase-space reconstruction is taken as a core, a causal analysis framework is provided by unifying GCA, and end-to-end modeling is realized. The final target is to generate a high-fidelity fMRI data model, so that the causal connection relationship is closer to a brain real neural mechanism, and the reliability and the application value of functional brain network research are improved.

The invention discloses a dynamic brain network analysis method guided by neural heterogeneity, and is suitable for the technical field of brain image processing and recognition. The method comprises the steps that functional magnetic resonance imaging data are acquired and preprocessed, an overlapped sliding window is used for dividing the functional magnetic resonance imaging data to construct a dynamic functional brain network, and then the dynamic functional brain network is decoupled into a topological consistency network and a time trend network which conform to brain activities; capturing space and time heterogeneity weights of different brain regions in the brain based on a topological consistency network and a time trend network, and identifying key nodes for driving brain network recombination; further weighting the topology consistency network and the time trend network to obtain a heterogeneity dynamic function brain network; propagation of neural information in a time dimension is simulated based on time propagation graph convolution operation, and spatial-temporal features of brain images are extracted from a heterogeneous dynamic function brain network; and finally, inputting the obtained spatial-temporal characteristics of the brain image into a multi-layer perceptron to predict the data category of the brain image to be recognized, and analyzing the influence of the brain disease image characteristics on the spatial-temporal heterogeneity of the brain region to complete the dynamic brain network analysis guided by the neural heterogeneity.

The application discloses a complex action-based spatio-temporal frequency domain feature fusion action recognition method and system. The application preprocesses the electroencephalogram signal of the complex action motor imagery paradigm, extracts the global spatio-temporal feature by using a time-space partition branch network TG-Net, extracts the frequency domain feature by using a frequency branch network F-Net for the power spectrum density of the preprocessed signal, and performs action recognition after flattening, splicing and the like of the frequency domain feature and the global spatio-temporal domain feature. The application constructs a time-space frequency domain double branch network, deeply fuses and splices the global spatio-temporal feature and the power feature, breaks through the limitation of the traditional method which is limited in the time-space domain, realizes the complementary feature extraction of the motor imagery electroencephalogram signal in the time, space and frequency dimensions, and adopts the partition weighting splicing mode of the functional brain area in the space dimension to highlight the important channel action recognition method, so that the comprehensive feature is acquired, and the classification precision is improved.

This invention relates to the field of brain function image classification and processing technology, specifically to an adaptive high-order fusion learning method for brain function image classification, comprising the following steps: S1, acquiring the brain function image to be classified and performing image data preprocessing; S2, constructing a high-order functional brain network matrix sequence; S3, adaptively learning the weights of different-order functional brain networks, weighted summing them to further output features; S4, capturing the contextual dependencies of the high-order functional brain network matrix sequence; S5, further extracting features and performing weighted fusion of features; S6, predicting and outputting the classification result; S7, parameter tuning. This invention, through end-to-end adaptive high-order functional brain network fusion learning, utilizes adaptive learning of different-order functional brain network weights to enhance the interpretability of the inference process between input features and prediction results, and captures temporal information before and after the generation of the high-order functional brain network matrix through a self-attention mechanism, accurately and efficiently classifying and identifying images of normal brain function and brain disorders.

An apparatus includes an intraosseous appliance formed to have hollow channels open to a proximal extradermal surface of the appliance. Optical emitters and detectors reside within channels of the intraosseous appliance having distal openings in a distal base of the intraosseous appliance, in a lateral surface of the intraosseous appliance, and in an extradermal surface of the intraosseous appliance, so as to establish optical paths between the optical emitters and detectors and, respectively, the dura, bone wall of a bun hole and skin of the subject. Intracerebral and extracerebral electrodes reside within respective channels of the intraosseous appliance having distal openings in the distal base of the intraosseous appliance and in the extradermal surface of the intraosseous appliance, respectively.

The invention discloses a brain network analysis method based on a multi-scale kernel attention mechanism, and the method comprises the following steps: carrying out the preprocessing of functional magnetic resonance imaging data, and obtaining a time sequence of each brain region; utilizing Pearson correlation to construct an initial functional brain network of each subject as an initial input feature of the model; performing feature extraction and analysis on the initial functional brain network based on an encoder of a multi-scale kernel attention mechanism; based on the prior knowledge of brain modularity, the output of the encoder based on the multi-scale kernel attention mechanism is aggregated and read by using an orthogonal clustering mode; and the classification layer outputs a final identification result. According to the method, a complex interaction relationship between brain regions is captured in a deep learning model in a flexible and interpretive manner, a high-level functional brain network can be effectively constructed, valuable information is provided for a recognition task, a biological marker can be effectively explored on the basis of improving the recognition performance, and the recognition efficiency is improved. The method has important theoretical significance and practical value.

A method for analyzing a user's behavioral, self-reported, and neural data to derive said user's neurobehavioral traits is disclosed. The method comprises: obtaining data associated with said user from a plurality of sources, wherein said data associated with said user comprises electroencephalography (EEG) data and said user's responses to one or more questionnaires; processing said data associated with said user to assess a range of functional brain measures or metrics by generating a model that is specific to said user's neurotype, wherein said neurotype comprises time-domain and time-frequency representations of said user's functional neural activity; and using said model to generate one or more predictive insights indicative of said user's neurobehavioral traits.

The invention relates to the technical field of medical image diagnosis, and particularly discloses a brain network analysis method based on time-space two dimensions and multiple scales, which comprises the following steps: obtaining a functional magnetic resonance image and extracting a time sequence of each brain region; on the basis of Pearson's correlation, functional homogeneity weighting is combined, and a functional brain map is constructed on fine, medium and coarse scales; multi-scale spatial features are extracted through a mixed structure of a U-Net encoder and a multi-scale graph isomorphic network; for a brain region BOLD signal, an internal and external dual-branch selective state space model architecture is adopted to respectively capture short-term instantaneous fluctuation and long-term trend dependence, and a time sequence fragment related to a pathological time sequence attention mechanism enhanced disease is extracted through a multi-scale context to obtain time features; and performing residual gating fusion on the spatio-temporal characteristics and then inputting the spatio-temporal characteristics into a classifier to obtain a classification result. According to the method, the limitation of single scale and single time sequence modeling is broken through, the refinement and functional fusion of the brain spatial-temporal characteristics are realized, and the accuracy and interpretability of brain disease auxiliary diagnosis are improved.

Disclosed herein are methods of determining a therapeutic for a patient with a psychiatric or neurological disorder, based upon the patient's functional brain imaging data through use of a generative model that predicts brain activity.

The invention discloses a time-space frequency domain feature fusion action recognition method and system based on complex actions. According to the method, electroencephalogram signals of a complex action motor imagery normal form are preprocessed, a space-time partition branch network TG-Net is used for extracting global space-time features, meanwhile, a frequency domain feature is extracted from the power spectrum density of the preprocessed signals through a frequency branch network F-Net, and the frequency domain feature and the global space-time domain feature are flattened, spliced and then subjected to action recognition. According to the method, the global spatio-temporal features and the power features are deeply fused and spliced by constructing the spatio-temporal frequency domain double-branch network, the design breaks through the limitation that the traditional method is mostly limited to the time-space domain, complementarity feature extraction of the motor imagery electroencephalogram signals in the three dimensions of time, space and frequency is achieved, and the accuracy of the motor imagery electroencephalogram signals is improved. And the spatial dimension adopts a partition weighted splicing mode of a functional brain region to highlight an action recognition method of an important channel, so that comprehensive features are obtained, and the classification precision is improved.

This invention relates to the field of brain network analysis technology, specifically to a multimodal brain network fusion method based on tensor spectral clustering. The method includes: acquiring multimodal brain network data, including structural magnetic resonance imaging (SMRI) data, functional magnetic resonance imaging (fMRI) data, and diffusion tensor imaging (DTI) data; preprocessing the multimodal brain network data; constructing individual morphological brain networks, functional brain networks, and structural brain networks based on the preprocessed multimodal brain network data, and performing normalization processing; fusing the normalized multimodal brain networks using a tensor spectral clustering algorithm to obtain a fused brain network; acquiring the subject's behavioral data, inputting the behavioral data into the fused brain network, and calculating the subject's behavioral prediction values. This invention not only advances research in neuroscience, cognitive science, and psychology but also provides strong support for related clinical applications and personalized medicine.

The invention discloses a large model semantic prompt guided dynamic brain network analysis method and system, and belongs to the application technology of a large model in a dynamic functional brain network. According to the method, semantic priori is introduced, brain region function semantic representations are constructed and aligned with node-level features, and subnet function semantic representations are constructed and aligned with subnet-level structures. On the basis, a time convolution module is constructed to simulate the time change process of the dynamic network. Furthermore, the subnet strength change semantics are used as prompt information to be injected into the model for adjusting the sensitivity of the time features to the stage change. Next, a spatial structure feature extraction module is constructed to further extract a stable topological structure relationship, and graph paper semantic information is introduced to assist in fusing topological features, so that the modeling capability of the model for the importance of a network structure is enhanced; and finally, inputting fusion features from a plurality of semantic hierarchies into a multi-layer perceptron to realize disease state classification, and based on semantic weight and feature contribution analysis, revealing the explanation ability of semantic priori on disease-related brain network changes.

The application relates to a system for realizing depression subtype classification processing based on deep learning multiple fusion brain network graph technology, wherein the system comprises the following modules: a data acquisition and processing module for acquiring resting-state functional magnetic resonance imaging data of a subject; a data preprocessing module for preprocessing the acquired data; a multiple functional brain network construction module for generating three functional connection matrices from obtained functional magnetic resonance imaging (fMRI) data and constructing a graph representation for each coefficient connected matrix; a multiple brain network graph fusion module for improving performance under small sample capacity by using a regularization term based on data enhancement and mapping each graph representation to a feature space by using GAT fusion area groups and difference pool area groups; and a depression subtype classification module for classifying depression subtypes. The application also relates to a corresponding method, device, processor and storage medium thereof. The system, method, device, processor and storage medium thereof help to further optimize the target intervention scheme of neural regulation technology in depression treatment.

The application provides a dynamic brain network clustering method and system based on nonlinear electroencephalogram signal feature fusion, and belongs to the cross field of neuroscience and information technology. The specific process of the method is as follows: data acquisition and processing: the electroencephalogram signals of a subject are collected by using multiple electrodes; dynamic cognitive network construction: the multidimensional electroencephalogram signals of each frequency band are divided by using a sliding window, the phase lock-in values of two groups of different channel electroencephalogram signals of the same frequency band in the same time window are obtained, a dynamic functional brain network is constructed, and a multi-frequency band multi-channel dynamic functional connection matrix is obtained; dynamic network clustering: each connection matrix is regarded as an independent cluster, the dynamic network clustering is realized by merging the two clusters with the shortest distance to form a new cluster, and a non-complete binary tree is formed; for the non-complete binary tree, starting from the topmost cluster, the clusters are accessed from top to bottom, the clusters are merged and removed, so that the clusters are within a set range interval, and finally the dynamic brain network clustering is realized.

Embodiments of the present application provide a brain image processing method, device, equipment and storage medium. The method comprises: determining a target classification feature of each brain region according to an imageomics feature and a functional brain network in a brain image; determining a corresponding target site according to the target classification feature of each brain region; and determining the functional connectivity of the target site according to the classification importance of each brain region facing the target site. The embodiments of the present application can realize accurate analysis of the functional connectivity of the target site of the brain, which helps to assist doctors in effectively analyzing the functional connection damage degree of the target site of the brain, thereby providing accurate clinical reference information for the analysis of the target site by the doctors.

The invention relates to a language area positioning method and device of a nuclear magnetic resonance imaging technology. According to the method, the structure nuclear magnetic image and the brain function nuclear magnetic image are obtained by scanning the detected person, the structure nuclear magnetic image and the brain function nuclear magnetic image are registered, the visual three-dimensional brain map is output, and the Pearson's correlation coefficient of the seed point is combined; the position of the core language area is judged by setting a proper selection threshold and combining the size of the selected area, and the classification of the core language area can be accurately judged.

The invention relates to a multi-modal prelingual emotion recognition system for a deaf person, and the system comprises an information collection and preprocessing unit, a functional brain network emotion recognition unit, a facial expression recognition unit, and an optimal decision fusion unit. The emotion of a deaf person subject is predicted through the methods of expression and electroencephalogram signal collection, signal preprocessing and calculation, facial area expression image processing, facial expression recognition, functional brain network emotion recognition and optimal decision fusion. Through fusion of a functional brain network and facial expression recognition, complex dynamic characteristics in electroencephalogram signals of the deaf people can be deeply analyzed, subtle emotional changes of the deaf people before speech are captured, the recognition accuracy and robustness are improved through an algorithm of adaptively adjusting the weight of each mode, and the method has relatively high precision and adaptability, and is suitable for popularization and application. And a more effective technical support is provided for emotion recognition of the deaf people.

The present invention relates to a device (20) for analyzing neuronal activity in a patient's brain by functional brain imaging in order to diagnose, assess, track, and / or classify a migraine condition of the patient. The device comprises an input (21) for receiving functional brain imaging data of the patient's brain and an output (22) for outputting at least one value. Furthermore, the device comprises a processor (23) for determining at least one activity measure that, based on the functional brain imaging data, indicates brain activity in at least one predetermined region of interest and / or between such regions of interest. The processor is designed to determine and output the at least one value based on (at least) the activity measures.The value(s) represent(s) a patient-specific migraine score, a classification of the migraine type, a prognostic / predictive value, an assessment of the influence of different types of migraine-triggering events and / or the efficacy and / or suitability of different treatments.

The invention relates to the technical field of brain function image classification processing, in particular to a brain function image classification method based on self-adaptive high-order fusion learning, which comprises the following steps: S1, acquiring a to-be-classified brain function image and performing image data preprocessing; s2, constructing a high-order functional brain network matrix sequence; s3, adaptively learning different-order functional brain network weights, and carrying out weighted summation on the different-order functional brain network weights to further output features; s4, capturing context dependence of the high-order functional brain network matrix sequence; s5, features are further extracted, and weighted fusion of the features is carried out; s6, predicting and outputting a classification result; and S7, adjusting and optimizing parameters. According to the method, through end-to-end adaptive high-order functional brain network fusion learning, the interpretability of an inference process between input features and a prediction result is enhanced by adaptively learning different-order functional brain network weights, and time sequence information before and after a high-order functional brain network matrix is generated is captured through a self-attention mechanism; and brain normal and brain disorder images can be accurately and efficiently classified and identified.

This invention discloses a brain network analysis method based on a multi-scale kernel attention mechanism, comprising the following steps: preprocessing functional magnetic resonance imaging (fMRI) data to obtain time series data for each brain region; constructing an initial functional brain network for each subject using Pearson correlation as the initial input features of the model; extracting and analyzing features from the initial functional brain network using an encoder based on the multi-scale kernel attention mechanism; aggregating and reading out the output of the encoder based on the multi-scale kernel attention mechanism using orthogonal clustering based on prior knowledge of brain modularity; and outputting the final recognition result from the classification layer. This method captures the complex interactions between brain regions in a flexible and interpretable manner within a deep learning model, effectively constructing high-level functional brain networks, providing valuable information for recognition tasks, and effectively exploring biomarkers while improving recognition performance, thus possessing significant theoretical and practical value.

The present application relates to the field of medical image analysis and computer-aided diagnosis of brain diseases, and proposes a dual cooperative learning brain network feature classification system and its training method, which specifically comprises: using an automatic anatomical labeling template, constructing static and dynamic functional brain networks based on the average time series signals of brain regions using Pearson correlation coefficients; using a dual-flow network to extract static and dynamic feature representations of the functional brain network; using a pruned and grafted Transformer module to dynamically adjust the features between the static and dynamic functional brain networks and their respective interiors; introducing a cooperative contrast loss function to learn high-level feature representations; and using a multi-layer perceptron to perform feature classification based on the output high-level features. The brain network feature classification system and its training method proposed by the present application not only significantly improve the feature classification performance, but also provide new insights into the interactive dynamics of brain activity.

The present application relates to the field of deep learning and emotion recognition, and discloses an EEG emotion recognition system and method based on multi-scale spatio-temporal graph convolution and contrast learning, which comprises the following steps: preprocessing the electroencephalogram (EEG) signal; constructing positive and negative sample pairs based on emotion categories and subject identities; extracting the hidden space representation of the EEG signal by using a stacked autoencoder, dividing the EEG signal into multiple functional brain regions to obtain the dimension-reduced brain-derived signals; constructing a non-directional graph structure of the brain-derived signals; constructing a multi-scale spatio-temporal graph convolution network as a feature extraction network, inputting the non-directional graph structure, dynamically learning and updating the adjacency matrix, expressing the features of the brain-derived signals in the non-directional graph structure, and extracting emotion-related features; and based on the multi-scale spatio-temporal graph convolution and contrast learning framework, building and training an EEG emotion recognition model to eliminate individual differences. The present application makes full use of the multi-dimensional information of the EEG signal, and significantly improves the accuracy, robustness and generalization performance of emotion recognition.

A method for achieving super-resolution in localizing electrical fields measured at the head surface with electroencephalography through a generative model of the cerebral cortex that has a very high resolution of cortical surface dipoles constructed from the known properties of human cerebral cortex and adapted to optimize the Bayesian explanation the individual's cortical surface electrical fields. The iterative optimization of the prior (generative) with the posterior (observed) fields with extensive data from extended recordings provides a probabilistic estimation of the individual's functional brain activity that can be used to train artificial neural network approximations of the individual's mental activity.

The invention discloses a multi-scale brain atlas construction method based on data driving, and relates to the technical field of biomedical engineering.The method comprises the steps that rs-fMRI data of different subjects are used for constructing a multi-scale brain atlas comprising different brain regions; respectively inputting the multi-scale brain atlas into feature extraction modules of different scales to obtain output features of corresponding scales; fusing the output features of different scales into a fused feature; carrying out average pooling operation on the fusion features to obtain global features; and classifying the global features by using a full connection layer to obtain label prediction results of different subjects. The multi-scale brain atlas constructed by the method has better scale adjustability and disease pertinence, a multi-level structure of brain function connection can be disclosed more comprehensively, and compared with a traditional AAL atlas, functional features of the brain can be captured more accurately, and the performance of a functional brain network in the aspects of flexibility and adaptability is improved.

The application discloses a depression image classification method based on a multi-modal dynamic graph convolutional neural network, belongs to the field of medical image processing and artificial intelligence, and utilizes a sliding time window method to divide a time sequence after functional magnetic resonance data preprocessing into multiple time windows, constructs a functional connection matrix of each window, utilizes multiple spatial attention contrast networks to capture time information across time windows, and obtains a high-order dynamic functional brain network; and utilizes a cross-modal graph neural network and cross-modal knowledge distillation to realize complementary information transmission and mode fusion between modes. The application can fully utilize dynamic high-order information of a multi-modal brain network to realize effective classification of depression.