756 results about "Brain function" patented technology

The invention discloses a tumor space occupying brain function partition nerve influence image segmentation method based on a deep learning model, and particularly relates to the technical field of artificial intelligence and medical cross. Comprising the following collaborative operation steps: multi-modal data fusion acquisition, tumor edge feature enhancement, anatomy-functional feature collaborative modeling, occupation deformation compensation, adversarial boundary optimization, dynamic loss regulation and control, cascade segmentation strategy, clinical interaction verification, and construction of a U-Net + + based improved three-dimensional feature fusion network. Utilizing a multi-scale cavity convolution module to extract edge gradient features of the tumor infiltration area in a layered manner; in order to solve the problem of multi-modal fusion and dynamic adaptation mechanism deficiency in the prior art, a three-dimensional cross-modal fusion network of a channel competition mechanism is constructed, multi-modal key features are dynamically screened through spatial pyramid pooling and soft attention weight, and a tumor volume self-adaptive dynamic loss function is combined, so that multi-modal fusion and dynamic adaptation are realized. The problems of feature confusion and poor generalization of a traditional method are solved.

The invention discloses a vagus nerve stimulation parameter closed-loop adjustment method and system based on electroencephalogram characteristics. The method comprises the steps that real-time electroencephalogram signals of a patient are obtained, and time domain information and frequency domain information of the electroencephalogram signals of all frequency bands in the real-time electroencephalogram signals are extracted; on the basis of the time domain information and the frequency domain information of the electroencephalogram signals of all the frequency bands, electroencephalogram signal index features are calculated, and the electroencephalogram signal index features comprise an electroencephalogram signal power spectrum, a brain dynamic symmetry feature, a brain function connection feature and a rhythm feature; determining the state type of the patient according to the electroencephalogram signal index characteristics; determining parameter configuration information of vagus nerve stimulation according to the state type of the patient; and adjusting parameters of the vagus nerve electrical stimulation equipment according to the parameter configuration information of vagus nerve stimulation. According to the invention, timely and accurate electrical stimulation can be applied to a patient, the treatment accuracy is improved, the stimulation efficiency and the treatment effect are enhanced, side effects are reduced, and more accurate and individualized treatment management is realized.

The invention relates to the technical field of brain function imaging, in particular to a target crowd recognition method and device based on neural blood flow feature multi-level fusion, and the method comprises the steps: collecting brain nerve blood flow signals of normal and target crowds by using synchronous EEG-fNIRS equipment, preprocessing and extracting single-mode features, and obtaining a single-mode feature set; a multi-frequency local nerve and blood vessel coupling analysis method is used for calculating nerve and blood vessel coupling strength characteristics, a space co-positioning method is used for unifying nerve and blood flow modal space information, the position precision is improved, and data layer fusion is achieved; and integrating and analyzing different modal feature space relationships by using a Yeo7 brain template to realize feature layer fusion, and finally training various machine learning classifiers by using significant difference features to realize identification of a target population. Therefore, the problems that in the prior art, macroscopic signal correlation is paid more attention to, so that analysis of the synergistic effect of cross-modal space information in a specific brain region is deficient, and deep understanding of a neurovascular function mechanism and brain region role revelation are restricted are solved.

The invention discloses a transcranial magnetic stimulation treatment individualized parameter optimization system based on artificial intelligence, and relates to the technical field of transcranial magnetic stimulation optimization systems. The transcranial magnetic stimulation treatment individualized parameter optimization system based on artificial intelligence comprises a data acquisition preprocessing module, a feature extraction module, a treatment parameter prediction module and a treatment effect evaluation module, and the data acquisition module is used for acquiring brain function data of a patient in real time; the feature extraction module is used for performing feature extraction on the preprocessed brain function data and clinical data; the treatment parameter prediction module is used for determining a treatment scheme suitable for the current condition of the patient according to the transcranial magnetic stimulation treatment parameter prediction result; the treatment effect evaluation module is used for continuously monitoring brain function data of the patient in the treatment process. The problems that in traditional transcranial magnetic stimulation treatment, parameter setting depends on experience and a general guide, individualized optimization and parameter adjustment are lacked, and consequently the treatment effect is inaccurate and the treatment time is long are solved.

The invention provides a spatial-temporal feature fusion-based dynamic graph convolution electroencephalogram depression detection method, which comprises the following steps of: firstly, segmenting a sample into fragments with the length of 1 second, and calculating power spectral density (PSD) as an input feature by adopting a Welch method; the time sequence and spatial characteristics of the EEG signals are synchronously extracted through a double-branch architecture, wherein one branch captures the long-term time sequence dependence of the EEG signals by using a GRU; and the other branch adopts an improved TSCN (separable convolution is introduced), multi-scale spatial features from fine to rough are extracted through causal convolution and expansion convolution of residual layered stacking, after double-branch features are adaptively fused based on an attention mechanism, a dynamic graph structure is constructed, functional connection evolution of brain intervals is modeled by using a graph convolution network, and a dynamic graph structure is constructed. The topological structure of the network is optimized through a back propagation process, and finally depression identification is realized through a Softmax classifier. According to the method, the time sequence modeling capability of the GRU and the multi-scale spatial analysis capability of the TSCN are fused, the representation limitation of a single model is broken through, the dynamic change of a brain function network is adaptively captured through dynamic graph convolution, the physiological interpretability is enhanced, deep complementary fusion of EEG spatial and temporal characteristics is realized, the depression recognition accuracy is remarkably improved, and the method is suitable for popularization and application. And an efficient tool is provided for auxiliary diagnosis of mental diseases.

The present disclosure discloses a multi-modal brain network calculation method, apparatus, device, and storage medium. The method is configured to train a brain disease prediction model. After the brain region structural feature and the brain region functional feature are separately extracted from magnetic resonance diffusion tensor imaging data and brain functional magnetic resonance data, a graph representation diffusion learning network is used to separate the universal feature and the unique feature in the brain region structural feature and the brain region functional feature. And then, multi-modal universal and unique feature fusion is implemented based on an alignment algorithm and adaptive weighting technology. Thus, complementary information between the multi-modal data is fully mining. The model can learn an effective feature of a related disease in a training process, and a finally obtained brain region disease prediction model has higher precision and better prediction effect.

The invention provides a multichannel transcranial direct current stimulation cognitive function assessment method and system, and belongs to the field of neuroscience and brain cognitive function assessment. The method comprises the steps that electroencephalogram signal data of a subject under multi-channel transcranial direct current stimulation are collected and preprocessed; respectively performing micro-state analysis, brain function connectivity analysis and oscillation power analysis on the preprocessed data; constructing a linear mixed effect model, and inputting the results of the micro-state analysis, the brain function connectivity analysis and the oscillation power analysis into the model for quantitative evaluation of the cognitive function state; and a time sequence database is constructed, and the time sequence database is used for storing cross-time-point analysis results and analyzing the long-term change trend of the cognitive function based on a statistical model. Dynamic, accurate and high-temporal-spatial-resolution evaluation of the cognitive state of the subject is achieved, the long-term change trend of the cognitive state is dynamically monitored, and technical support is provided for early warning and rehabilitation effect tracking of neurodegenerative diseases.

A user workload state processing method and apparatus based on multimodal data, and a device. The method comprises: acquiring state information of a first user; determining workload information of the first user on the basis of the acquired state information, wherein the state information comprises at least two of the following information: physiological information, eye movement information, electroencephalogram information, brain function imaging information, motion capture information, spatiotemporal acquisition information, behavior acquisition information, and facial expression and state information; and feeding back the workload information to a first management account, and formulating a training scheme matched with the workload information. According to the embodiments of the present application, workload of users can be identified on the basis of multimodal data of users.

The invention discloses a Parkinson's dyskinesia individualized SCAN network positioning method based on a multi-modal image and deep learning. The method comprises the steps of obtaining multi-modal medical image data, preprocessing the multi-modal medical image data, obtaining a multi-modal structure image and functional connection data, and calculating a spontaneous neural activity index of a whole-brain voxel level; taking a priori brain region related to the spontaneous neural activity index and dyskinesia as a seed point, constructing a seed point voxel function connection graph representing individual brain function connection, and performing nonlinear feature fusion and extraction through the deep learning network model; the bilinear attention network is adopted to capture the interaction information of the feature data and the individual dyskinesia symptom which is significantly related, an individualized SCAN network positioning result is obtained, the structure-function coupling characteristics of the individual brain are comprehensively described, the cross-modal pathological features related to the dyskinesia can be more sensitively recognized, and the accuracy and accuracy of the diagnosis and treatment of the dyskinesia can be improved. And the accuracy and robustness of abnormal brain region detection are obviously improved.

The invention discloses a method for establishing a clinical interpretable PD diagnosis model based on multi-sequence magnetic resonance brain characteristics, and aims to promote more accurate diagnosis of PD by extracting multi-level and multi-dimensional brain image information from multi-modal brain magnetic resonance image data and constructing a diagnosis model by means of machine learning. The method comprises the steps of brain image data preprocessing, feature standardization and screening, model construction, independent verification set and cross-disease set verification, a group of brain function and metabolism features taking a PD abnormal perfusion mode and nigra iron distribution as the principal thing are obtained, and the constructed model has high diagnosis efficiency in a training set and the independent verification set. Secondly, clinical interpretability of the model is promoted through curve calibration, DCA and CIC analysis and correlation analysis of predicted individual scores obtained based on the model and clinical symptoms. The diagnostic efficiency of the constructed PD diagnostic model in different disease sets shows that the model has good diagnostic efficiency on PSP and MSA diseases.

The invention discloses a respiratory training quantitative evaluation method, which comprises the following steps of: acquiring physiological parameter characteristics related to heart rate, respiration and brain function of a human body through a human body physiological data acquisition platform, and performing dimensionality reduction, dimensionless processing and weighted summation on the characteristics to obtain a respiratory training quantitative evaluation result. The method comprises the following specific steps: firstly, collecting human heart rate, respiration and brain function related physiological features through a physiological parameter collection platform, then calculating feature classification weight of each dimension through random forest and cross validation and removing redundant feature dimensions, and then removing dimensions of features in a feature subset through a dimensionless method; and finally, performing weighted summation on the feature data through the feature weight to obtain a respiratory training quantitative evaluation result. Quantitative evaluation is carried out on respiratory training, so that people can be helped to formulate more scientific respiratory training strategies and methods.

The invention discloses a GNN-based multi-mode brain imaging infantile autism spectrum disorder detection method, which is characterized in that a function connection network which is different from traditional characteristics and takes an edge as a center is introduced, higher-order information interaction in a brain interval is mined, and a brain function abnormity mode of an infantile autism patient is accurately captured. Meanwhile, integrating brain imaging data and clinical text information into a unified multi-modal graph by utilizing the graph structure learning ability of GNN, capturing a complex nonlinear relationship, and realizing deep combination of multi-modal features; according to the method, the accuracy and robustness of autism detection are effectively improved, technical support is provided for personalized diagnosis and treatment, key technical problems in multi-modal data fusion and brain network analysis are solved, and the accuracy and reliability of ASD early diagnosis are improved.

Methods and devices for changing a brain state of a person from an initial brain state to a target brain state are described. The method comprises the following steps: receiving information representing the initial brain state, wherein the information comprises the structural composition and the functional architecture of the brain; estimating a likelihood of the brain changing from the initial brain state to the target brain state based at least in part on the received information; determining a non-invasive brain stimulation scheme based at least in part on the received information and the estimated likelihood of the brain changing from the initial brain state to the target brain state; and controlling at least one non-invasive brain stimulation device to stimulate the brain according to the non-invasive brain stimulation scheme. The method also includes using the brain information to provide information for a design to compute a generic artificial intelligence agent.

The invention relates to the technical field of medical information extraction, in particular to an image feature selection method for a schizophrenia medical record Spark model. The method comprises the following steps: acquiring brain magnetic resonance image data and resting state functional magnetic resonance imaging data of a plurality of subjects; performing multi-scale layered segmentation on the brain image of each subject by using a preset layered brain region template for the brain magnetic resonance image data to obtain brain region positioning data including a local level, a regional level and a global level; and performing adaptive hierarchical noise reduction processing on the resting state functional magnetic resonance imaging data in a Spark distributed environment to obtain brain function time sequence data after noise reduction. According to the method, the brain magnetic resonance image data is accurately divided into a local level, a regional level and a global level by using the preset layered brain region template, so that local structure details and global network characteristics of the brain region are considered, and effective integration of multi-scale information is realized.

The invention provides an attention deficit hyperactivity disorder recognition system based on a brain function connection group development norm, which is used for classifying and recognizing attention deficit hyperactivity disorder by constructing the brain function connection group development norm and utilizing an obtained brain function connection individual development deviation index. The invention provides an attention deficit hyperactivity disorder recognition system based on a brain function connection group development norm. According to the method, a norm of brain function connection characteristics changing along with age is constructed, the degree of an individual deviating from a normal range is described, and the attention deficit hyperactivity disorder patient is identified based on an obtained individualized deviation index, so that a quantitative and individual-level novel brain imaging biological marker is provided for the attention deficit hyperactivity disorder patient. In norm construction, the Bayesian spline regression method used in the method can more accurately model nonlinear distribution by combining B spline transformation, and meanwhile, the calculation time can be shortened, so that the method can be efficiently expanded to a large brain image data queue and can be flexibly applied to new sites which are not included in training samples.

The invention provides a brain function evaluation method and system based on fNIRS and eye movement feature fusion, and the method comprises the steps: testing a to-be-tested person under a pre-constructed social scene normal form, and obtaining test data which comprises functional near infrared spectrum data and eye movement data; extracting time dynamic characteristics of brain function activation and brain function network space organization mode characteristics from the functional near infrared spectrum data, and constructing a near infrared brain function characteristic set; for a near-infrared brain function feature set corresponding to the functional near-infrared spectrum data and an eye movement space-time feature set corresponding to the eye movement data, constructing features in each near-infrared brain function feature set and features in the eye movement space-time feature set into feature pairs, and calculating a correlation coefficient of each feature pair, feature fusion and screening are realized based on correlation coefficients; and inputting the screened features into a classification evaluation model to obtain the severity of the behavioral dysfunction and a brain function analysis value.

The invention discloses a brain function excitation inhibition state evaluation method, which comprises the steps of detection tool selection, signal acquisition, preprocessing, characteristic parameter extraction and result evaluation, the detection tools comprise electroencephalogram, functional near infrared spectrum imaging and functional magnetic resonance imaging, the detection tools are selected according to the adaptability of a patient, and a treatment strategy is customized in a personalized manner. The method has high pertinence, and the brain function state of the patient can be rapidly evaluated; by extracting a plurality of characteristic parameters as an evaluation basis, the dynamic attributes of the brain are comprehensively considered, and the accuracy and comprehensiveness of a detection result are ensured; and meanwhile, based on assignment of characteristic parameters, dynamic changes of the brain regions can be evaluated in real time during interaction between the brain regions, and the accuracy and reliability of a detection result are ensured by deeply considering and integrating dynamic characteristics of the brain.

The invention relates to the technical field of anesthesia management, in particular to an anesthesia medicine excess brain function influence assessment system applying artificial intelligence, which comprises a data acquisition module, a data preprocessing module, a model training module, a real-time assessment module, a risk early warning module, a treatment suggestion module, a system interaction module and a remote monitoring module. Through the combination of a convolutional neural network and a long-short-term memory network, spatial-temporal characteristics of brain wave and functional magnetic resonance imaging data are extracted, a brain function thermodynamic diagram is generated in real time, and the influence of anesthetic drugs is analyzed; the system is combined with a reinforcement learning algorithm to dynamically adjust the anesthetic dosage, a risk early warning module dynamically adjusts a threshold value through physiological parameters and tolerance of a patient, an expert team can provide medical assistance in real time through a remote monitoring module, and brain function safety of the patient in the operation or anesthesia process is ensured; according to the invention, the safety, accuracy and individuation level of anesthesia management are effectively improved.

Methods and apparatus for changing a brain state of a person from an initial brain state to a target brain state are described. The method includes receiving information characterizing the initial brain state, the information including a structural composition and a functional architecture of the brain, estimating based, at least in part, on the received information, a potential for the brain to change from the initial brain state to the target brain state, determining based, at least in part, on the received information and the estimated potential for the brain to change from the initial brain state to the target brain state, a non-invasive brain stimulation protocol, and controlling at least one non-invasive brain stimulation device to stimulate the brain according to the non-invasive brain stimulation protocol. The method also includes using brain information to inform the design of computational general artificial intelligence agents.

The invention provides a transcranial deep electrical stimulation closed-loop regulation and control system and method based on fNIRS dynamic guidance. The method comprises the steps that a transcranial alternating current electrical stimulation module applies an electrical signal to a target deep brain region according to preset parameters to carry out electrical stimulation regulation and control; the synchronous triggering module is used for realizing millisecond-level synchronization of a stimulation task and near-infrared brain function data acquisition; the brain function monitoring module analyzes the concentration change of cortex oxyhemoglobin in real time through the multi-channel head cap; the electrical stimulation-response coupling mapping module positions a significant activation channel by adopting statistical test, and establishes an oxyhemoglobin concentration variable and electrical stimulation current amplitude quantitative model; and the dynamic parameter adjusting module optimizes the output current in real time. Personalized closed-loop regulation and control of non-invasive deep brain stimulation can be achieved, cerebral cortex blood oxygen signals are monitored in real time through near-infrared brain function imaging, stimulation parameters are dynamically adjusted, and the accuracy and individualization level of deep brain stimulation are remarkably improved.

The invention discloses a disturbance of consciousness stimulation regulation and control system and method fused with electroencephalogram connection recognition. The system comprises a simulated electroencephalogram signal data acquisition stage, a connection recognition analysis stage, a stimulation parameter optimization stage and an executable stimulation instruction conversion stage. The method has the following advantages and effects that a whole-electroencephalogram activity distribution diagram is generated by simulating an electroencephalogram signal data acquisition stage, a key connection area is identified, and a brain function connection map is generated by utilizing a function connection analysis network and a phase synchronization algorithm in a connection identification analysis stage; in the stimulation parameter optimization stage, space-time correlation between a whole electroencephalogram activity distribution map and a brain function connection map is established, a multi-objective optimization algorithm is adopted to generate an optimized stimulation parameter set through a fusion network, and finally, in the executable stimulation instruction conversion stage, the optimized stimulation parameter set is converted into an executable stimulation instruction based on a self-adaptive control model. Therefore, the accuracy and the self-adaptive capability of electroencephalogram signal stimulation regulation and control are remarkably improved.

The invention discloses a technology for targeted stimulation of a specific brain region and application of the technology in regulation and control of brain functions, and belongs to the field of animal cognitive behavior research. Techniques for targeted stimulation of specific brain regions include insulated stimulation electrodes that can generate AC voltage stimulation and a stimulation device for adjusting the AC voltage intensity and frequency. By applying the technology (ntTMS) for targeted stimulation of the specific brain region, an obvious magnetic stimulation effect can be achieved in the center of the brain region, cerebral neurons of a target region are activated, social and cognitive behaviors of animals are effectively regulated and controlled, and no obvious side effect is brought to experimental animals.

The invention is applicable to the technical field of brain discipline, and provides a brain function connection modeling and coding method, device and equipment and a storage medium, the method comprises the following steps: constructing a first brain function connection graph according to rs-fMRI data, performing graph enhancement processing on the first brain function connection graph by adopting a preset adaptive graph enhancement strategy to obtain a second brain function connection graph, performing feature coding on the second brain function connection graph by adopting a preset topological attention coding strategy to obtain corresponding graph features, and performing feature projection on the graph features by adopting a preset feature projection strategy to obtain brain function discrimination features for brain function connection classification, therefore, the generated brain function discrimination features can accurately identify subtle differences of different types of brain function connections, and high-accuracy discrimination can be realized whether normal and abnormal brain function states or brain connection modes corresponding to different diseases, so that powerful support is provided for clinical aid decision making, and the accuracy of brain function discrimination is improved. And the accuracy and scientificity of brain disease diagnosis and treatment can be improved.

The invention relates to the technical field of medical instruments, in particular to a sleep monitoring system based on a non-invasive brain oxygen saturation monitor, which comprises a monitoring system and is used for synchronously and dynamically monitoring local brain oxygen in real time, and the monitoring system comprises a non-invasive brain oxygen dynamic monitoring unit used for monitoring the brain blood oxygen saturation of a patient in real time by adopting a near infrared spectrum technology; the multi-parameter synchronous analysis unit is used for integrating the brain oxygen data, the electroencephalogram signals, the cerebral blood flow data and the respiratory event indexes; the intelligent risk assessment engine analyzes a brain oxygen change rule based on a deep learning algorithm, and predicts a brain function impairment risk caused by sleep breathing disorder; in the intelligent risk assessment engine, on the basis of a space-time convolutional neural network, brain oxygen time sequence data and spatial distribution characteristics are combined, and a brain hypoxia mode of the OSA patient is recognized; the method has the characteristic of realizing early warning of the brain injury related to sleep breathing disorder through noninvasive brain oxygen monitoring, multi-parameter fusion analysis and intelligent risk assessment.

The invention discloses a transcranial electrical stimulation physiotherapy system based on EEG-fNIRS feedback. The transcranial electrical stimulation physiotherapy system comprises an EEG-fNIRS signal acquisition and processing module, a relaxation degree evaluation module, a transcranial electrical stimulation control module and a transcranial electrical stimulation execution module. The transcranial electrical stimulation physiotherapy system provided by the invention can accurately extract spatial and temporal characteristics related to relaxation degree, constructs a personalized brain function network model, accurately locates stimulation sites and neural activity modes based on the characteristic that EEG and fNIRS data complement each other in terms of advantages in terms of time resolution and spatial resolution, and improves the rehabilitation effect of the brain function network model on the basis of the characteristic that the advantages of the EEG and fNIRS data complement each other in terms of time resolution and spatial resolution. The method realizes personalized dynamic adjustment of the relaxation degree, and is suitable for multiple fields of education, medical treatment, rehabilitation and the like.

Disclosed are devices, systems and methods for acquiring, analyzing, and utilizing neurofeedback to promote brain coherence. Neurofeedback is a form of biofeedback that allows an individual to regulate his / her brain activity by providing a visual metaphor of brain function, thereby making it accessible for manipulation. In some embodiments of the present technology, a system includes a brain signal detection device wearable by a subject and a computer device including a display and a brain-computer interface (BCI) configured to monitor brain signals and display visual, auditory, and / or tactile stimuli to the subject according to a neurofeedback threshold-based protocol to deliver brain signal coherence between the left and right hemispheres of a subject's brain.

The present invention discloses a technology for measuring brain function suitable for an infant or a moving subject who cannot be controlled easily during measurement. One embodiment of the present disclosure pertains to an ultrasound device that comprises: multiple ultrasound probes that receive / transmit ultrasound signals from / to multiple brain areas via multiple head regions and are disposed corresponding to the respective head regions; a control unit that controls the respective ultrasound probes; and an image processing unit that generates brain function network information calculated from blood flow states among the respective brain areas based on measurement results acquired from the respective ultrasound probes.

The invention discloses a depression brain function connection data analysis method based on multi-map fusion, is applied to the field of deep learning and nerve imaging, and aims to solve the problem that depression brain function connection cannot be represented accurately and effectively in the prior art. According to the method, brain region level blood oxygen concentration dependency signals are obtained from resting state functional magnetic resonance imaging data based on a plurality of brain maps divided according to different scales or functions, and then a functional connection matrix of each map is obtained through calculation based on a correlation algorithm; and then abstracting the functional connection matrix into graph structure data, carrying out feature extraction by using a multi-scale graph convolutional layer, and finally fusing and analyzing multi-map features by using two different strategies of multi-head cross attention fusion and adaptive map weight learning, so as to execute downstream tasks such as diagnosis or biomarker positioning. According to the method, multi-map information of functional magnetic resonance imaging is well integrated, the reliability of a depression brain function connection analysis result is improved, and an objective reference is favorably provided for clinic.

The invention belongs to the field of electroencephalogram signal classification detection, and particularly relates to a neuropsychiatric disease electroencephalogram diagnosis method based on iteration polar coordinate attention, which comprises the following steps: acquiring a multi-channel EEG (electroencephalogram) signal and preprocessing the multi-channel EEG signal; inputting the EEG preprocessing signal into a pre-trained improved LaBraM model to obtain a plurality of node features; calculating a Pearson's correlation coefficient matrix and a cosine similarity matrix according to the EEG preprocessing signal, and then constructing a brain function fusion connection matrix as an adjacent matrix through an iteration polar coordinate attention mechanism; according to the method, the large-scale pre-trained EEG model and polar coordinate attention are used for brain graph structure construction for the first time, and collaborative optimization of time feature generalization and space structure modeling capacity is achieved.

The invention discloses a multi-mode autism diagnosis method and system based on resting state fMRI and phenotypic text information, a medium and a product. FMRI and phenotypic text information are processed through a pre-trained heterogeneous graph neural network model to output a diagnosis result; the resting state fMRI is utilized to construct a brain function connection graph, and the phenotypic text information is coded into a two-dimensional vector; respectively extracting brain connection feature embedding of the fMRI mode and phenotype information feature embedding of the text mode; fusing the feature embedding in the two modes through a gating fusion network; and constructing a heterogeneous group diagram based on the fusion features and phenotypic information similarity, and obtaining group diagram features on the heterogeneous group diagram by using dual-channel information aggregation and adaptive feature fusion to output a diagnosis result. The invention aims to improve the accuracy of autism diagnosis by using multi-modal information, and can be applied to the fields of neuroimaging analysis, intelligent medical treatment and the like.