72 results about "Neural imaging" patented technology

The invention provides an EEG function connection prediction method based on fMRI deep cross-modal representation learning, and relates to the crossing field of neuroiconography and artificial intelligence. According to the method, a sample pair is constructed through time alignment of EEG and a blood oxygen level dependent signal, an end-to-end deep neural network architecture composed of a time projection unit, a cross-attention fusion encoder and a connection synthesis head is designed, and direct mapping from a BOLD signal to EEG function connection is achieved. The model adopts a composite loss function, and gives consideration to the consistency of the prediction connection matrix with the real EEG function connection in numerical precision and topological mode, thereby achieving the high-fidelity reconstruction of the EEG function connection map at the frequency domain level. According to the invention, the topological structure stability of the brain function network can be effectively maintained. Under the conditions of incomplete EEG data, serious noise interference or complete loss, the frequency domain function connection characteristics can still be stably recovered, and a reliable analysis substitution path is provided for brain function network research.

The invention relates to the technical field of medical image processing, in particular to a multi-time-point neural image comparative analysis method and system.The method comprises the following steps that a first three-dimensional neural image matrix and a second three-dimensional neural image matrix are obtained, rigid transformation matrix registration is calculated, and a third three-dimensional neural image matrix is generated; constructing a three-dimensional elastic grid model and adjusting node coordinates based on a mutual information criterion; generating a three-dimensional displacement vector field; constructing a Jacobian matrix and calculating determinant values; executing natural logarithmic transformation to generate a microscopic volume change rate map; and calculating a logarithm Jacobian mean value and determining a volume change state. According to the method, pose deviation is eliminated by calculating a rigid transformation matrix, a vector field reflecting fine displacement is constructed by utilizing a mutual information criterion, voxel-level quantitative analysis is realized in combination with a Jacobian matrix and logarithmic transformation, and minimal lesion recognition precision and diagnosis efficiency are improved in cooperation with a standard brain anatomy template.

The invention relates to a brain anomaly network positioning method and system based on functional connection network mapping in the technical field of neural image data processing. The brain abnormal network positioning method comprises the following steps: calculating a whole brain function network diagram connected with each abnormal site by using resting state function connection data of large-scale health subjects based on a plurality of dispersed abnormal sites reported in previous literatures; then superposing the function network diagrams to obtain a network probability graph; and finally, filtering the probability graph through a threshold value to obtain a final core anomaly network graph. According to the method, the inherent functional connection architecture of the brain is used as a reference system, abnormal sites which seem to be uncorrelated in different researches are successfully traced and unified to a common and stable functional network, and compared with a single brain region marker, the generated network-level biomarker integrates more source evidences, so that the network-level biomarker has the advantages that the network-level biomarker can be widely applied to the field of biomarkers of the brain region. Therefore, the problems of result heterogeneity and inconsistency in brain abnormality discovery are solved.

The invention relates to a method for determining an individualized nerve regulation target spot, and the method comprises the steps: obtaining nerve image data, which are repeatedly measured for multiple times, of a subject and corresponding clinical psychological assessment data in a preset time period; calculating a brain activity index of each voxel in a preset brain region; establishing a plurality of candidate mathematical models to describe the relationship between the brain activity indexes and the clinical scores; selecting an optimal model through statistical test of fitting residual errors; generating a parameter weight map representing'symptom-activity 'association strength based on the optimal model; and finally, determining an individualized nerve regulation target according to the numerical distribution of the map. The invention also relates to a corresponding device, a processor and a computer readable storage medium thereof, and solves the problem of inaccurate target positioning caused by neglecting symptom heterogeneity and individual brain function difference in the prior art through a core methodology of ''longitudinal tracking-multi-model fitting-residual optimal selection''. The curative effect of nerve regulation and control treatment is obviously improved.

The invention discloses a neural signal extraction self-supervised learning method and system based on sparse decomposition, belongs to the technical field of deep learning computer image processing, and solves the problems that in an existing traditional neural signal extraction method, calculation time is long, and in an existing deep learning neural signal extraction method, calculation time is short. Signals need to be labeled manually; and the extraction accuracy is low. Comprising the following steps: obtaining a denoised neural microscopic image as a data set; constructing a sparse decomposition network, and training the sparse decomposition network by adopting a loss function; inputting the denoised neural microscopic image into the trained sparse decomposition network for reasoning to obtain a sparse part image representing neuron information; drawing an F / F image, performing threshold segmentation processing, and extracting spatial positions of neurons; according to the spatial positions of the neurons, F / F time sequence signals of each neuron are extracted, and the spatial position and starting and ending time of each neuron event are recorded; the method is suitable for a neural imaging technical scene.

The invention discloses a sparse electroencephalogram signal source positioning method based on functional magnetic resonance guidance, and relates to the crossing field of electroencephalogram signal processing and neuroimaging technologies. The method mainly comprises three parts of fMRI-guided sparse source space construction, subject specificity forward model construction and multi-target regularization inverse problem solving. The method comprises the following steps: firstly, screening high-activation voxels through BOLD signal intensity of fMRI, and constructing a sparse source space through connected component analysis and representative point selection; then, a subject specific boundary element (BEM) head model is constructed based on the structural MRI, and electrode registration and lead field matrix calculation are completed; and then a multi-target regularization model fusing data fidelity, space compactness and intensity consistency is constructed, optimal estimation of source current intensity is obtained through analysis and solution, and finally a positioning result of brain power activation is output. According to the method, the advantages of high time resolution of the EEG and high spatial resolution of the fMRI are fully played, the limitations of inverse problem morbidity, low spatial resolution and insufficient multi-mode fusion in traditional brain power supply positioning are effectively solved, and brain power supply positioning with high precision, noise resistance and high interpretability is realized; and a new scheme is provided for cognitive neuroscience research, nervous system disease diagnosis and brain-computer interface development.

This invention relates to the field of intelligent brain disease diagnosis technology, specifically providing an auxiliary diagnostic method and system based on multimodal decoupled dynamic graph learning. The method includes: acquiring and preprocessing multimodal data (such as neuroimaging, genetic markers, etc.) of the subject; extracting common pathological information and modality-specific features through a shared encoder and modality-specific encoders respectively, and optimizing the separation process using a decoupling loss function; furthermore, fusing all modality embeddings using a multi-head self-attention mechanism with a masked matrix to generate initial node representations, where the mask is used to suppress modality self-attention; subsequently, performing hierarchical dynamic graph convolution based on the node representations: in each layer, dynamically updating the graph adjacency matrix by combining the current node representation with the original features, and iteratively optimizing the node representations through message passing; finally, inputting the optimized representations into a classifier to obtain disease prediction results. This invention improves the automation performance and reliability of diagnosis.

The invention discloses an ADHD child food addiction neural mechanism evaluation method based on fMRI, and the evaluation method mainly comprises the following steps: obtaining the test results of the attention, execution function, intelligence quotient and food addiction of to-be-evaluated children, and dividing the to-be-evaluated children into an ADHD with food addiction group, an ADHD without food addiction group and a health control group according to the results; performing fMRI stimulation normal form execution after grouping, and performing brain function data acquisition; and finally, constructing a mathematical model of neural image data analysis, so that a specific neural circuit of ADHD children food addiction and a mechanism modulated by an emotional state can be revealed non-invasively and objectively, and an important scientific basis and tool are provided for early recognition, pathological mechanism research and targeted intervention strategy development of ADHD co-disease food addiction.

This invention relates to a multimodal data fusion method for modality missing, wherein the method includes the following steps: (1) acquiring multimodal data, including at least two of neuroimaging data, text data, and numerical data, wherein modality missing exists in the multimodal data; (2) inputting the multimodal data into a pre-trained multimodal data fusion model for feature encoding and cross-modal feature fusion processing to obtain fused features containing multimodal information; (3) outputting personalized risk prediction results through a risk prediction module using the acquired multimodal fusion features. This invention also relates to a corresponding system, device, processor, and computer-readable storage medium thereof. Using the multimodal data fusion method, system, device, processor, and computer-readable storage medium of this invention for modality missing, cross-modal adaptive modeling of patient multimodal data is performed to achieve accurate efficacy prediction.

The application discloses a multi-modal deep learning source tracing method and system combining magnetoencephalogram and electroencephalogram, relates to the field of artificial intelligence and neuroimaging technology, and inputs real magnetoencephalogram signals and electroencephalogram signals into a source tracing model after preprocessing, predicts the probability of the occurrence of corresponding regional sources, combines an imported source partition distance matrix, and obtains a final source tracing result; the training process of the source tracing model is as follows: a generative adversarial network is constructed to generate a multi-modal neuroelectrophysiological data set; the multi-modal neuroelectrophysiological data set is input into a double-branch structure residual network to perform stage hierarchical extraction and decoupling on the magnetoencephalogram signals and the electroencephalogram signals respectively; a multi-scale convolution module is used to extract features at different stages, the extracted features are input into a classifier after being fused, and a loss function is defined to update trainable parameters of the source tracing model; and the source tracing method improves the accuracy and generalization ability of source positioning.

The invention discloses a plateau population brain aging comprehensive index determination method and device, a medium and a computer program product, which adopt a 3D-CNN architecture to process nerve image data, improve brain age prediction precision, apply a longitudinal comparative analysis method, realize individualized brain aging trajectory tracking, generate a saliency map, and improve brain age prediction accuracy. And visual abnormal brain region positioning information is provided. And a multi-modal weighted fusion algorithm is adopted, so that data isomerism challenges are overcome, and information complementation and result verification are realized. Brain oxygen saturation parameters are incorporated into a brain aging evaluation system, and the key problem that hypoxia affects brain aging in a plateau environment is solved. A plateau population brain aging norm is established, the problem that plain standards are not applicable is solved, and a plateau brain aging specific mode is disclosed. The integrated evaluation process simplifies the operation steps, reduces the professional threshold, improves the prevention and treatment effect through personalized intervention suggestions, and is beneficial to delaying the brain aging process.

The invention provides a cerebral cortex thickness measurement method and system based on a level set image segmentation algorithm, and belongs to the technical field of neural image analysis, and the method comprises the steps: obtaining a brain magnetic resonance imaging image, and carrying out the skull stripping processing; performing three-dimensional visualization on the stripped image through volume rendering, and acquiring three-dimensional coordinates of points of interest and a region of interest on the surface of the cortex by using a preset interaction means; using a level set method to carry out brain grey matter and brain white matter segmentation on the region of interest to obtain a brain grey matter segmentation layer and a brain white matter segmentation layer, and storing three-dimensional coordinate data of points in the segmentation layers; calculating the minimum Euclidean distance according to the three-dimensional coordinate data of the points in the segmentation layer and the three-dimensional coordinates of the points of interest to obtain the cortex thickness of the points of interest; the method solves the problems that the existing cerebral cortex thickness measurement lacks a visual means, is not supported by a mathematical model, cannot be accurate to the thickness of an interest point, and cannot display and retain comprehensive information.

This invention provides a method and system for predicting brain diseases by fusing amplitude and phase information with graph-aware hybrid expert graph neural networks. It relates to the field of neuroimaging analysis technology. The method includes: acquiring raw resting-state functional magnetic resonance imaging (fMRI) data of a subject and corresponding brain disease category labels; preprocessing the raw resting-state fMRI data; extracting the mean oxygenation level dependent signal time series of multiple brain regions of the subject and using the mean oxygenation level dependent signal time series as the signal time series; constructing a functional connectivity matrix and a phase adjacency matrix based on the signal time series; constructing a training dataset; constructing a brain disease prediction model based on a two-branch hybrid expert graph neural network; training the brain disease prediction model using the training dataset; acquiring resting-state fMRI data; inputting the resting-state fMRI data into the trained brain disease prediction model for prediction, and outputting the brain disease prediction result.

The invention relates to the technical field of intelligent brain disease diagnosis, and particularly provides an auxiliary diagnosis method and system based on multi-modal decoupling dynamic graph learning, and the method comprises the steps: obtaining and preprocessing the multi-modal data (such as nerve images and genetic markers) of a subject; common pathological information and modal unique features are extracted through a shared encoder and modal specific encoders respectively, and a decoupling loss function is utilized to optimize a separation process. Furthermore, a multi-head self-attention mechanism with a mask matrix is adopted to fuse all modal embedding, a node initial representation is generated, and the mask is used for inhibiting modal self-attention. Then, hierarchical dynamic graph convolution is carried out based on node characterization, in each layer, a graph adjacency matrix is dynamically updated in combination with current node characterization and original features, and the node characterization is iteratively optimized through message passing; and finally, inputting the optimized representation into a classifier to obtain a disease prediction result. According to the invention, the automation performance and reliability of diagnosis are improved.

The invention discloses an Alzheimer's disease preclinical risk quantitative evaluation method and system, and belongs to the technical field of deep learning. The method comprises the steps of data preprocessing, model construction, model training and evaluation, image thermal region mapping and the like. According to the method, a quantitative evaluation model covering NC, SCD, MCI and AD stages is constructed based on a cognitive feature and neural image bimodal enhanced fusion method and a Grad-CAM-based interpretive loop, the classification precision is improved, a key region of interest of neural image MRI in the Alzheimer's disease stage is mapped, and the classification accuracy is improved. Therefore, reference is provided for auxiliary diagnosis of Alzheimer's disease development.

The invention relates to the technical field of neural image analysis, and particularly provides a brain function connection intelligent screening method and system for autism spectrum disorders, and the method comprises the steps: firstly obtaining resting state functional magnetic resonance imaging data and phenotype information thereof, and extracting a blood oxygen level dependence value time sequence of each brain region after preprocessing; then constructing a multi-scale brain network comprising a low-order function connection matrix and at least one high-order function connection matrix; the matrix is converted into a brain function connection graph containing sub-graphs of different scales through threshold sparsification; meanwhile, phenotype embedding features are extracted from phenotype information; the graph data and the phenotypic features are input into a multi-channel neural network model for parallel processing and fusion, and joint feature representation is obtained; and finally, outputting an auxiliary diagnosis result of the autism spectrum disorder through the classifier. According to the method, by fusing the multi-scale brain function connection information and the individual phenotype features, the accuracy of autism classification diagnosis and the generalization ability of the model are effectively improved.

The application discloses a short-term memory discrimination method based on multi-modal neuroimaging and deep learning, and comprises the following steps: S1, synchronizing an EEG-fMRI device to collect electroencephalogram signals and BOLD signals in a resting state and a memory task; S2, pre-processing the data collected in the step S1; S3, extracting feature data of the EEG and the fMRI through a convolutional neural network; S4, fusing the feature data of the EEG and the fMRI through position coding and attention mechanism weighting to generate a joint feature vector; and S5, classifying the joint feature vector based on an ELM algorithm to output a memory state discrimination result.The application has the beneficial effect that the fMRI and EEG data obtained through collection and fusion are combined with the CNN and ELM algorithms to realize high-precision memory state classification, the correlation analysis is performed with a behavioral result, the short-term memory characteristic signal is discriminated by using neuroimaging data, and the neural mechanism of memory coding and consolidation is analyzed.

The invention discloses a control method, system and equipment for anesthesia prognosis optimization and a storage medium, and relates to the technical field of biomedical engineering. The cognitive function evaluation data, the brain structure image data and the brain function image data of the patient before the operation are calculated, and a cognitive expression index and a nerve image index are obtained; calculating the neural image index and the cognitive performance index to obtain a cognitive reserve index; determining the risk level of the target patient according to the cognitive reserve index, and inputting the physiological data of the patient and the risk level into a technology library for query to obtain a core regulation and control technology; adjusting the stimulation parameters of the core regulation and control technology according to the cognitive reserve index, and generating a noninvasive nerve regulation and control scheme according to the core regulation and control technology, the adjusted stimulation parameters and the stimulation target; and sending the non-invasive nerve regulation scheme to non-invasive nerve regulation equipment to control the non-invasive nerve regulation equipment to intervene the target patient before the operation. By implementing the technical scheme provided by the invention, the stress ability of the brain of the patient to surgical anesthesia is improved.

The invention discloses an interpretable MRI (Magnetic Resonance Imaging) image analysis method and system based on anatomical constrained attention, and relates to the field of medical image intelligent analysis and computer-aided diagnosis. According to the method, Hadamard product fusion is carried out on a neural image anatomical region mask and spatial attention, depth feature mining is guided by anatomical structure constraints, and the depth feature mining accuracy is improved. The attention of the model focuses on a disease specific area; a single-channel ResNet50 is adopted to adapt to MRI gray scale characteristics, and key slice dynamic screening and weighted fusion strategies are combined, so that the calculation time is shortened, and rapid and accurate research and judgment are realized; and a thermodynamic diagram is generated through fusion of multi-scale Grad-CAM and anatomical priori knowledge, so that the interpretability is enhanced. According to the invention, a high-precision and interpretable intelligent solution is provided for efficient identification and auxiliary diagnosis of NIID rare diseases and hydrocephalus.

The disclosed system provides an integrated neuroimaging analytics platform for comprehensive preoperative neurosurgical planning, intraoperative neurosurgical guidance and post-operative assessment by processing multimodal MRI (structural, diffusion, functional, and angiography) and CT data. The platform performs detailed anatomical characterization by delineating tumor subregions (peritumoral edema, enhancing tumor, and necrotic core), segmenting brain tissues (gray matter, white matter, and CSF), and executing lobe, cortical / subcortical parcellation. Advanced 3D rendering visualizes tumors alongside critical white matter fibre tracts derived from diffusion MRI, while MRA data is used to segment cerebrovascular structures, and functional MRI analysis identifies eloquent cortices associated with motor, speech, and visual functions. All results are integrated within a user-friendly GUI featuring advanced multiplanar slicing and a smart brush for interactive mask editing, complemented by a speech-to-text engine for streamlined analytical reporting. This comprehensive approach facilitates precise and efficient surgical planning, thereby enhancing patient safety and improving clinical outcomes.

A computer-implemented method and system includes accessing neurophysiological and neurovascular data recorded during sleep. A function mapping is executed from said neurophysiological and neurovascular data to a target that is one of a glymphatic flow marker, a molecular analysis marker of neurodegeneration, or a neuroimaging marker of neurodegeneration. A target prediction model is output based on the function mapping. The target prediction model can receive new neurophysiological and neurovascular data and output a predicted marker of neurodegeneration.

This invention relates to a method, apparatus, device, and medium for classifying cognitive states based on multimodal neural signals. The classification method includes: acquiring electroencephalogram (EEG) information from a subject and preprocessing it to obtain a standardized EEG feature matrix; mapping the matrix using an EEG encoder from a pre-trained variational autoencoder to generate an enhanced feature representation containing high-resolution neural image information; inputting the matrix into a multi-task expert hybrid model decoder, dynamically allocating weights through a routing network, and calling multiple functionally specialized expert networks for processing to obtain a weighted integrated expert output; mapping the matrix to a classification space to output the classification result of the subject's cognitive state. This method achieves endogeneous feature enhancement of EEG signals through cross-modal deep fusion and simultaneously constructs an expert hybrid decoding architecture that conforms to the principle of brain functional partitioning, significantly improving the accuracy of cognitive state classification.

The application relates to the technical field of medical health, and provides an AD early warning model construction method and system based on multi-dimensional testing, which comprises the following steps: collecting neural image data, biomarker data and clinical feature data of a plurality of subjects, screening abnormal data of the neural image data set, performing data cleaning on the biomarker data set, performing data coding on the clinical feature data set, respectively extracting features from the pretreated neural image data set and the pretreated biomarker data set to obtain a neural image feature set and a biomarker feature set, constructing a multi-dimensional feature matrix set, obtaining a weighted multi-dimensional feature matrix set by using a training set matrix subset and a test set matrix subset, training a clinical prediction model by using the weighted multi-dimensional feature matrix set, obtaining an early warning experimental model, and testing the early warning experimental model to obtain an early warning model. The application can solve the problems of low diagnosis precision of a single data source and abnormal data interference.

The application discloses a depression relapse risk intervention method, device, equipment and medium, and belongs to the medical technical field. The method comprises the following steps: integrating a gene risk score, a neural imaging brain region feature and clinical history data through a multi-modal fusion neural network to generate an individualized baseline risk score; dynamically correcting the baseline score based on self-evaluation data to enhance the real-time performance of risk assessment; analyzing the time sequence characteristics of physiological and behavioral data by using an LSTM time sequence model to output a short-term relapse early warning label; and combining real-time voice / text data emotion knowledge graph analysis and dynamic risk grading to trigger a hierarchical intervention strategy. The application solves the problems of single evaluation dimension and response lag of traditional methods through a multi-dimensional data fusion and dynamic calibration mechanism, realizes closed-loop management from risk warning to precise intervention on the premise of avoiding direct clinical diagnosis, and improves the comprehensiveness and timeliness of depression relapse prevention and control.

The application relates to the technical field of neural image processing, and particularly discloses a brain atlas division system based on a multi-modal multi-dimensional lateralization index similarity network. The method first performs spatial uniform random sampling on the left hemisphere cortical surface of an individual, and extracts the 5-layer neighborhood of the sampling points by using the grid topological connection relationship; then, according to the cross-hemisphere vertex correspondence, the symmetric neighborhood is positioned in the right hemisphere, and the lateralization index (LI) distribution of the cortical features is calculated; by kernel density estimation modeling and morphological counter divergence algorithm, the LI-MIND correlation matrix representing the whole brain symmetry is constructed; finally, the spectral clustering algorithm is used for feature decomposition and dimension reduction of the matrix, the optimal clustering number is determined according to the contour coefficient, and the smooth individualized brain region division atlas is generated. By introducing the topological neighborhood and the lateralization distribution characteristics, the problem that the traditional brain atlas cannot effectively capture the individual organization left-right hemisphere difference is solved, and the brain region division scheme depending on the lateralization information is provided.

A non-invasive computer-aided system and method for assessing the severity of autism spectrum disorders across multiple assessment modules use as input neuroimaging data of a subject brain, parcellates the subject brain into a plurality of brain regions, identifies neuroimaging markers denoting connectivity between regions, determines connectivity between regions, identifies regions associated with autism spectrum disorder, and uses machine learning techniques to determine the severity of autism spectrum disorder with respect to each module based on the determined connectivity.

The invention discloses a brain level dynamic analysis and virtual intervention method based on thalamus-cortex functional gradient, and belongs to the technical field of neural image analysis and mental disease calculation modeling. The invention aims to solve the problems that the existing research cannot systematically reveal the time sequence damage of thalamic cortex connection in disease development, cannot describe a cortex hierarchy compression mechanism, and lacks a simulation framework for theoretical intervention verification. A set of comprehensive analysis process integrating large-sample multi-center resting state fMRI, functional gradient mapping, sensory movement-highlight network-joint cortical axis construction, cortical separation coefficient calculation and virtual intervention simulation is provided to identify systematic anomalies of the thalamic cortical network in schizophrenia. And the key function of the highlighting network in the hierarchical structure damage process is analyzed. The cross-disease course, multi-scale and multi-network integration method established by the invention can systematically describe the hierarchical recombination process from the sensory region to the joint region in schizophrenia, and provides an innovative technical path for understanding disease neural basis, identifying disease course stage characteristics and exploring potential intervention targets.

Neural imaging helmets include the placement of a number of sensors, such as in a sensor array on and around the helmet. The placement and orientation of the sensors puts them close to the participant's head for best neural image capturing. As people's head size and shape varies, moving the sensors from one helmet to another can be onerous. Therefore, connecting the sensors and associated cables together allows for efficient removal and replacement of the sensors and cables. The use of sensor holders connected to another will aid in ensuring proper orientation and location, regardless of the helmet used. This will allow different sized helmets to be readily prepared for use with neural imaging devices.

The invention belongs to the technical field of medical image processing, and discloses a neural image space-time coding method based on dynamic curriculum learning, which comprises the following steps: S1, inputting a three-dimensional slice image and preprocessing the three-dimensional slice image; s2, performing approximate sorting pooling space-time coding on the preprocessed slice image, and outputting a reconstructed two-dimensional dynamic graph; s3, performing hierarchical and intra-stage iterative training based on a dynamic course learning strategy to realize adaptive stage switching; s4, based on a dynamic grouping mechanism, adaptive dynamic channel remarking and space attention remarking are carried out, and final output of the corresponding stage is obtained; and S5, after all stages are completed, processing results are sent to a task head for classification, segmentation or regression. The method is suitable for a computing power limited environment, clearly displays the evolution process of the features from macroscopic to microscopic, accords with clinical diagnosis logic, and obviously improves the classification accuracy.