13 results about "Brain dysfunction" patented technology

The invention discloses a multi-mode brain dysfunction auxiliary diagnosis method based on a dynamic function connection network. A two-stage collaborative learning framework from an individual brain graph to a group relation graph is constructed. Firstly, an individual multi-modal fusion brain map is constructed, node features of the individual multi-modal fusion brain map are obtained through node regularization regression analysis of an rs-fMRI time sequence, an adjacent matrix is obtained through calculation of the brain interval grey matter volume difference of a T1 image, and individual enhancement characterization is obtained through map convolutional network fusion. And then constructing a group relationship enhancement graph, taking individual representation as node features, constructing a dual-channel adjacency relationship for distinguishing homologous / heterologous connection according to age and gender, obtaining final discriminative representation through dual-channel graph attention network aggregation, and performing classification diagnosis according to the final discriminative representation. According to the method, deep fusion of multi-modal information and explicit modeling of key biological variables are realized, and an effective tool is provided for accurate and explainable auxiliary diagnosis of brain diseases.

The system according to the embodiment aims to appropriately grasp the toilet timing of people with dementia or higher brain dysfunction, thereby reducing the burden on caregivers. [Solution] A system according to an embodiment includes a collection unit, an analysis unit, and a calling unit. The collection unit collects data on the subject using a motion sensor, a heart rate sensor, and a body temperature sensor. The analysis unit understands the subject's condition based on the data collected by the collection unit and predicts when the subject will need to go to the toilet. The calling unit uses a caregiver avatar to call out to the subject and guide them to the toilet based on the analysis results obtained by the analysis unit.

The invention discloses an ADHD diagnosis system and method fusing neurodynamic enhancement and domain adaptation. The method belongs to the technical field of medical image processing and artificial intelligence crossing. The technical problems that an existing ADHD diagnosis method is low in recognition accuracy, poor in generalization ability and poor in robustness and interpretability are solved. The system comprises a data input and preprocessing module, a neural quality-chaotic disturbance module, a mutual information minimization domain adaptation module and a multi-modal graph convolutional network module. Nonlinear dynamic characteristics of brain activity are captured through the nerve quality-chaos disturbance module, domain differences of multi-site data are effectively eliminated through the domain adaptation module, sample correlation consistency is guaranteed through graph structure constraint loss, the dynamic characteristics can correspond to pathological mechanisms of brain dysfunction, and an interpretable basis is provided for clinical diagnosis.

The ability to communicate smoothly with many people who have higher-order brain dysfunction. [Solution] A display device (glasses 1) worn on the head of a user with higher brain dysfunction is characterized by comprising: an audio input means (microphones 23, 24) for inputting sound, an image input means (camera 21) for inputting images, and a processing means (processing unit 13) that inputs sound and / or images and performs processing to support brain function due to higher brain dysfunction, in the event that a specific part of the user's brain is damaged.

The application discloses an information processing method and device for brain dysfunction auxiliary analysis, equipment and medium, relates to the technical field of data analysis, and comprises the following steps: acquiring initial functional magnetic resonance data, and preprocessing the initial functional magnetic resonance data to obtain target functional magnetic resonance data; generating feature data of each brain region based on the target functional magnetic resonance data, and determining the target importance of each brain region and the target correlation between each brain region based on the feature data; determining the target spatial coding of each brain region based on the comparison result of each target correlation and a preset threshold, and constructing a target graph structure coding based on the target importance, the target correlation and the target spatial coding of each brain region; generating enhanced features based on each target graph structure coding and each feature data, determining a classification result based on the enhanced features, and generating and outputting a brain dysfunction analysis result by using the classification result. The application can improve the accuracy of functional magnetic resonance data classification and meet the medical image analysis demand.

The present invention relates to a brain dysfunction and seizure detector monitor and system, and a method of detecting brain dysfunction and / or seizure of a subject. Preferably, the present invention also includes one or more seizure detection algorithms. The analysis method is specifically optimized to amplify abnormal brain activity and minimize normal background activity yielding a seizure index directly related to the current presence of ictal activity in the signal. Additionally, a seizure probability index based on historical values of the aforementioned seizure index, is derived for diagnostic purposes. The seizure probability index quantifies the probability that the patient has exhibited abnormal brain activity since the beginning of the recording. These indexes can be used in the context of emergency and / or clinical situations to assess the status and well-being of a patient's brain, or can be used to automatically administer treatment to stop the seizure before clinical signs appear.

Provided are a computer program with which the privacy of a subject can be protected, an information processing device, and an information processing method.　This computer program causes a computer to execute processing for acquiring brain wave data of a subject from a brain wave sensor attached to the subject, determining whether the brain waves of the subject are normal or abnormal on the basis of the acquired brain wave data, setting a watching unit for watching over the subject to an ON state in accordance with the brain wave determination result, and executing a determination test for determining brain dysfunction using watching data acquired from the watching unit.

A system and method is provided for acquiring data from a brain of a subject and analyzing the data to generate an indication of a level of acute impairment of the subject.

A system for evaluating a degree of brain dysfunction of a subject, such as a decline in cognitive function, calculates a difference in movement functions between both hands in a coordination movement. The system includes a storage device for storing time-series data on a finger movement task of each of both hands of a test subject acquired by a movement sensor; a data processing device for analyzing the time-series data stored in the storage device; and a display device for displaying an analysis result analyzed by the data processing device. The data processing device includes a movement waveform generation unit for generating a movement waveform corresponding to the time-series data stored in the storage device; and a difference-between-hands feature quantity generation unit for generating a difference-between-hands feature quantity which represents a difference in respective finger movement tasks between both hands, based on the respective movement waveforms of both hands.

The invention discloses a brain dysfunction identification method based on ultrasonic Doppler blood flow. The method comprises the following steps: acquiring sample data containing neck artery blood flow characteristic parameters and blood oxygen saturation characteristic parameters; calculating the relevance proportion weight of the characteristic parameters and the brain dysfunction based on a characteristic weight fusion algorithm of information entropy and local distribution dependency; key feature parameters are selected according to the relevance proportion weight; cleaning data containing key feature parameters by a robust data cleaning method integrating unsupervised density estimation and supervision label guidance; using the cleaned data as a training set to train a random forest model; and inputting key characteristic parameters measured by the ultrasonic Doppler blood flow equipment in real time into the trained random forest model, and outputting whether the patient has brain dysfunction or not by the model. According to the method, comprehensive analysis of the cerebral hemodynamic parameters and the blood oxygen saturation can be achieved under the non-invasive condition, and the accuracy and the real-time performance of brain dysfunction recognition are improved.

A composition for preventing and / or improving brain dysfunction, especially Alzheimer's disease is provided. The composition includes dihydromyricetin or salts thereof, L-theanine, taurine, and cerebroside, which can enhance the intestinal stability and bioavailability of dihydromyricetin and prevent and improve brain dysfunction through multiple mechanisms such as anti-inflammation, inhibition of DNA methylation, elimination of hematoma, and removal of Aβ. In addition, the composition can be used in combination with monoclonal antibody drugs to reduce adverse reactions such as cerebral edema and cerebral hemorrhage that may occur during the treatment of Alzheimer's disease.

The invention discloses a traditional Chinese medicine composition for treating sepsis encephalopathy. The traditional Chinese medicine composition is prepared from the following raw material medicines in parts by weight: 20-40 parts of ginseng, 6-18 parts of raw rhubarb, 20-40 parts of sargentgloryvine stem, 20-40 parts of dandelion, 20-40 parts of monkshood and 3-9 parts of leech. The traditional Chinese medicine composition has the effects of tonifying qi and restoring yang, relaxing bowels and detoxifying, and promoting blood circulation and removing blood stasis, and clinical tests show that the traditional Chinese medicine composition can remarkably improve the clinical score, inflammatory response and brain dysfunction degree of sepsis-related encephalopathy patients, relieve nerve injury and improve 28-day prognosis, and shows good effectiveness and safety. In addition, the invention further discloses a preparation method and application of the traditional Chinese medicine composition.

Methods for preventing or treating brain neuronal diseases are provided. The methods include administering mesenchymal stem cells having increased agouti-related peptide (AgRP) expression or a conditioned medium thereof to a subject in need thereof. In some embodiments, the conditioned medium contains AgRP. The methods may further comprise administering ghrelin. The brain neuronal diseases include Alzheimer's disease, frontotemporal dementia, tauopathy, Parkinson's disease, amyotrophic lateral sclerosis, Huntington's disease, multiple sclerosis, stroke, thrombosis, embolism, head trauma, cerebral circulatory or metabolic disorders, brain dysfunction, and dementia.