54 results about "Imaging brain" patented technology

The invention provides a multi-mode nuclear magnetic resonance image glioma segmentation method and application thereof, and belongs to the field of medical image processing. The invention provides an M2ES-UNet network aiming at the problems of insufficient utilization of spatial features, single multi-modal fusion mechanism and cross-level semantic loss of an existing segmentation method. According to the method, multi-view anatomical information is extracted through a multi-plane feature collaboration module; utilizing an orthogonal dimension fusion convolution and modal introspection-collaboration module to respectively realize differential fusion of shallow and deep features; and the progressive jump transmission of the features is realized through a coding information smooth transmission module. According to the method, multi-plane and multi-mode complementary information can be effectively mined, the boundary precision and robustness of brain glioma segmentation are remarkably improved, and clinical diagnosis is assisted.

The present invention describes an artificial intelligence (AI) enabled electroencephalography (EEG) system that integrates Pathway Hierarchical Adaptive Referencing (PHAR) for localized signal detection, large language models (LLMs) for automated EEG reporting, and Internet of Medical Things (IoMT) connectivity for adaptive neuromodulation control. The system can also deliver transcranial electrical stimulation (tES) pulses and function as an electrical impedance tomography (EIT) system. PHAR employs a multi-layered multiplexer hierarchy and adaptive referencing topologies to optimize EEG signal acquisition and spatial resolution. LLM integration enables automated generation of human-readable EEG reports. IoMT connectivity allows closed-loop neuromodulation, where real-time EEG analysis guides the adjustment of stimulation parameters. The system can deliver tES pulses and perform EIT expands its functionality, allowing for targeted neuromodulation and impedance-based brain imaging. This integrated system revolutionizes EEG-based diagnostics, treatment, and research in neurology and neuroscience, offering a comprehensive and versatile tool for understanding and modulating brain function.

The invention discloses a light field reconstruction brain image brain region boundary extraction method based on convex hull fitting. The method comprises the steps that the p percentile of a brain image is calculated, and image cutting, contrast stretching and Gaussian filtering smooth denoising are carried out; carrying out Canny edge detection on the filtered image to obtain a binary edge image; boundary enhancement and connection are carried out through expansion and closed operation, all connected regions are extracted, and the contour with the maximum area is selected as the contour of the brain region boundary; a datum point is determined based on the contour of the brain region boundary, the polar angle and distance of each point except the datum point are calculated and sorted, and convex hull fitting is carried out through Graham Scan scanning based on the datum point and the sorted point set; converting the convex hull into a closed boundary region, and obtaining a mask image of the brain image after light field reconstruction through a mask function; according to the method, the special boundary form of the light field reconstruction image can be accurately adapted, deep learning and data training are not needed, and the generated mask has high geometric consistency.

The invention discloses a multi-mode nuclear magnetic image brain tumor segmentation system based on optical flow method pixel correlation, relates to the field of image processing, and solves the problems that complex physiological correlation among multiple modes cannot be captured and specific characteristics of a tumor area are difficult to reproduce in an existing missing mode completion method. The segmentation system comprises a data preprocessing module, a cross-modal optical flow estimation module, a pixel association weight calculation module, a missing modal complementation module and a fusion segmentation module. The system is simple in structure and reasonable in design, breaks through the limitation that a traditional optical flow model depends on a gray level consistency hypothesis, and adapts to the characteristic that the gray level difference of the multi-mode MRI is remarkable. By capturing the consistency of the gray gradient direction of the same anatomical structure in different modals, cross-modal pixel correlation mapping is accurately established, optical flow estimation deviation caused by gray mismatching is avoided, a reliable correlation basis is provided for subsequent deletion completion, and the accuracy of cross-modal information transmission is guaranteed.

A method for assessing a patient's brain disease state from brain images includes acquiring the brain images, partitioning them into predefined regions based on anatomical landmarks, extracting disease-indicative features, using a pretrained model to generate a disease-associated biomarker from the features, and determining the patient's brain disease state based on the biomarker.

The invention discloses a modeling and intervention simulation method and system for children with difficulty in reading and writing Chinese based on a digital twin brain technology. A data acquisition module acquires behavior data and brain imaging data of children with difficulty in reading and writing Chinese and normal contrast children; constructing a Chinese read-write digital twin base model by using a model construction module, and simulating function shunting and consciousness formation dynamics in a brain read-write process; the individualized modeling module adopts a double constraint optimization method to carry out individualized fine tuning on the Chinese read-write digital twinborn base model and establish an individualized digital twinborn model; the intervention simulation module carries out verification and mechanism analysis on the individualized digital twinborn model, simulates different intervention strategies, predicts the improvement effect of the intervention strategies on individual read-write behaviors and brain characterization, and recommends and outputs an individualized intervention scheme; aiming at individual digital twinning modeling with difficulty in reading and writing in Chinese, an exclusive individual digital twinning model is constructed for each tester, and individual heterogeneity with difficulty in reading and writing is analyzed.

The invention relates to the technical field of neural regulation and control, in particular to a dynamic cognitive regulation and control system which is suitable for dynamic cognitive regulation and control of different types of task paradigms, and for the dynamic cognitive regulation and control of each type of task paradigm, the system comprises the following modules: a cognitive function task module, a cognitive function task module and a cognitive function task module, the mapping module is used for establishing a mapping relation between a task normal form and a cognitive function and a mapping relation between the cognitive function and a brain functional area; the data analysis module is used for analyzing the cognitive function behavior data and the cognitive function brain imaging data to obtain behavior indexes and brain imaging characteristics; the regulation and control module is used for executing cognitive regulation and control on the user according to regulation and control parameters set by the judgment result of the cognitive aging risk probability of the user; and the evaluation module is used for comparing the current training result of the user with the historical training result to obtain an evaluation result, and dynamically adjusting the regulation and control parameters of the next round of cognitive regulation and control according to the evaluation result to realize dynamic monitoring and regulation and control of cognition.

The application claims a kind of neonatal brain imaging system and method based on photoacoustic technology, belong to the field of medical devices. Including control module, excitation source module, neonatal brain photoacoustic data acquisition module, data output module and quantitative calculation module. The control module includes two computers and laser control instrument;The excitation source module includes high-frequency laser and its water cooling system;Neonatal brain photoacoustic data acquisition module contains focusing lens and optical fiber, wearable flexible ultrasonic transducer, multichannel acquisition card;The data output module contains computer matched with real-time imaging MarsonicsDAQ software and the imaging algorithm embedded in the software;Quantitative calculation module contains multispectral linear demixing algorithm and imaging software. The application provides high-resolution, high-contrast real-time imaging of neonatal brain tissue structure and cerebral hemodynamic parameters, which can be used as a complementary method to existing brain imaging techniques for auxiliary diagnosis.

The invention relates to the field of fluorescent dyes, in particular to a near-infrared fluorescent dye for brain imaging as well as a preparation method and application of the near-infrared fluorescent dye. The near-infrared fluorescent dye for brain imaging has the advantages of novel structure, good biocompatibility, large Stokes shift, high light stability, high fluorescence signal-to-noise ratio and the like; the near-infrared fluorescent dye prepared by the invention is simple in preparation process, mild in reaction condition, short in synthesis path and beneficial to industrial production, and has a wide application prospect.

Disclosed herein are systems and methods for evaluating the underlying molecular (e.g., brain reward system molecules) cause for a depressive disorder and developing a treatment plan based on the identified molecular cause. In one or more examples, the systems and methods described herein can utilize any combination of brain imaging techniques, subjective emotion data taken from a patient, and / or one or more algorithms for translating emotional states to brain reward system molecules (e.g., neurotransmitters) to determine an underlying molecular cause for a depressive disorder of a patient. Once the underlying molecular cause of the depressive disorder of the patient is determined, a treatment plan that includes both behavioral and pharmacological aspects can be selected based on the identity of the reward system molecule that is determined to be deficient and the level of deficiency.

This application discloses a method, apparatus, storage medium, and electronic device for evaluating the signal quality of fNIRS (functional optical brain imaging). The method includes: acquiring incident light intensity data and emitted light intensity data emitted by a light source; determining the coefficient of variation based on the incident light intensity data, and determining the signal-to-noise ratio based on the incident light intensity data and the emitted light intensity data; processing the incident light intensity data to obtain the number of peaks and heartbeat signal characteristics within a preset frequency range; and determining the quality evaluation result of the fNIRS signal based on the coefficient of variation, signal-to-noise ratio, number of peaks, and heartbeat signal characteristics. The evaluation method of this application can comprehensively measure the quality of near-infrared signals and can adapt to the physiological characteristics of different individuals to guide real-time signal quality detection and iterative hardware design.

The present application relates to the technical field of risk assessment, and particularly relates to a neurodegenerative disease risk assessment method based on brain imaging technology, comprising obtaining brain imaging data of a subject in a resting state, a controlled neural disturbance state and a recovery state after the disturbance is removed, and performing same-region registration and time sequence alignment processing on the brain imaging data to generate a baseline brain network atlas, a disturbance response offset sequence and a recovery rebound sequence. The present application constructs a multi-level evaluation mechanism of fragile nodes-unstable propagation path-whole brain vulnerability cumulative value, jointly calculates the node vulnerability weight and the brain network propagation intensity, quantifies the overall stability of the brain network, and outputs the risk level and the priority degenerative brain area, realizes systematic evaluation from local brain area abnormalities to whole brain network risk, and improves the network-level analysis capability of neurodegenerative disease risk prediction.

The invention provides an MRI (Magnetic Resonance Imaging) image brain partitioning method and device. The method comprises the following steps: constructing a training model, inputting training data into the training model for histogram statistical analysis, and estimating initial mixed model parameters by utilizing histogram analysis and a clustering algorithm; inputting brain MRI data into the training model, and performing coarse segmentation according to expectation maximization parameter estimation and histogram fitting; constructing an MRF model according to the initial hybrid model parameters and an MRF potential energy function, iterating a coarse segmentation result, and updating the initial hybrid model parameters; stopping iteration until the parameters of the initial hybrid model reach a convergence condition, otherwise, resetting the parameters of the initial hybrid model, and carrying out iteration again; in the iteration process, the model parameters can be adaptively adjusted according to the current segmentation result; the adaptive strategy enables the algorithm to better deal with noise and other complex conditions in the image, and at the same time maintains a high identification rate for different brain tissue types.

The present disclosure relates generally to medical imaging and, more particularly, it relates to methods and systems for performing processing of magnetic resonance (MR) imaging of the brain which may be useful in the diagnosis of cognitive disorders. More specifically, the invention includes methods for processing cortical diffusion data from a region of a subject's brain, comprising determining values for the Axial Columnar Refraction (ACR) using values for AngleR and Axial Diffusivity.

The utility model discloses an fNIRS brain imaging device and system, the device specifically comprises a soft sleeve, the inner side of the soft sleeve is provided with two board card slot rows, each board card slot row comprises a plurality of rubber card slots, and the two board card slot rows are spaced by a first preset distance; the number of the rubber clamping grooves of the two board card slot rows is the same, and the adjacent rubber clamping grooves in each board card slot row are spaced by a first preset distance. A control module; a plurality of detection board cards, one detection board card is arranged in one rubber card slot, and each detection board card comprises a transmitting module and a receiving module which are oppositely arranged; the transmitting module is used for transmitting an initial waveform to a brain area of a user, and the transmitting module can transmit the initial waveform to any direction; the receiving module is used for receiving a detection waveform obtained after the initial waveform passes through a brain area; in each detection board card, the transmitting module and the receiving module are spaced by a first preset distance. According to the utility model, the brain area of the user can be comprehensively detected.

Accurate characterization of brain tissue microstructure using diffusion MRI (dMRI) data relies on optimal scanning protocols. A framework to optimize dMRI protocols for sophisticated multicompartment tissue models is based on the Cramér-Rao lower bound (CRLB). The framework is capable of capturing features like axonal diameter index and multiple fiber orientations in a voxel. The framework can handle any number of model parameters, including water diffusivities, enhancing estimation fidelity. Leveraging automatic differentiation and parallel computing, the framework is capable of systematically exploring the entire parameter space for comprehensive scanning rotocol optimization. By optimizing the data acquisition, this framework can significantly enhance biophysical modeling accuracy in dMRI, thereby deepening understanding of brain tissue properties in health and disease.

A compact portable quantum sensor device consists of a very high efficiency RF antenna, a low power RF signal generator, an RF amplifier (if needed), an RF switch and isolator, a photodetector(s) with amplifier circuit, various optical components, a microcontroller, a Bluetooth communication board, a battery, a display, and control software and machine learning algorithms for noise reduction and data analysis. A battery-operated portable quantum sensor device prototype was built for magnetometry applications. A second prototype with a smaller sensor head footprint was also built for brain imaging through measuring magnetic fields induced by brain neuron action potentials. In a third photonic circuit approach, all of the optical and electronic components are integrated on the same chip.

There is provided a system and method for generating a mapping of local brain cell activity and connectivity. The method including: receiving brain imaging data from image captures of a brain; generating a binary segmentation map using a trained deep learning model, the deep learning model taking the brain imaging data as input; performing registration of the brain imaging data to a brain template; voxelizing the segmentation map and warping the voxelized segmentation map using deformations obtained during registration; determining group-wise heatmaps of neuronal density or cellular density from the voxelized and warped segmentation map; generating a map of clusters of between-group differences in neuronal density or cellular density from the group- wise heatmaps of the voxelized and warped segmentation map; and outputting the map of clusters as a representation of local brain cell activity and connectivity.

The application provides a multi-modal nuclear magnetic resonance image brain glioma segmentation method and application thereof, and belongs to the field of medical image processing.The M2ES-UNet network is provided in view of the problems of insufficient space feature utilization, single multi-modal fusion mechanism and cross-level semantic loss of existing segmentation methods.The method extracts multi-view anatomical information through a multi-plane feature coordination module;orthogonal dimension fusion convolution and mode introspection-coordination modules are used to realize differentiated fusion of shallow and deep features;and the encoding information smooth transmission module is used to realize progressive jump transmission of features.The application can effectively mine multi-plane and multi-modal complementary information, significantly improve the boundary precision and robustness of brain glioma segmentation, and assist clinical diagnosis.

The embodiment of the invention provides a detection method and device based on self-confident degree, equipment and a medium, and relates to the technical field of data processing. The method comprises the following steps: acquiring a to-be-detected image; acquiring brain imaging data and a first detection result of the user according to the to-be-detected image; inputting the brain imaging data and the first detection result into a self-confidence degree decoding model to obtain a first self-confidence degree which is output by the self-confidence degree decoding model and corresponds to the first detection result; inputting the to-be-detected image into the detection model to obtain a second detection result output by the detection model; according to an analysis process of outputting a second detection result by the detection model, determining a second self-confidence degree corresponding to the second detection result; and determining a comprehensive detection result according to the first self-confident degree, the second self-confident degree, the first detection result and the second detection result. Therefore, the method can improve the detection efficiency and accuracy.

The application relates to a micro brain imaging device for dual-color fluorescence and an imaging method thereof, and relates to the technical field of biomedical imaging devices.The device comprises a connected shell and a lens end cover, and an imaging light path and an illumination light path are sequentially arranged inside the shell and the lens end cover along an imaging optical axis.The imaging light path comprises a lens group, a first dichroic mirror, a first filter and a fifth lens which are sequentially arranged.The lens group is composed of a first lens, a second lens, a third lens and a fourth lens which are sequentially arranged.The illumination light path comprises a first light source, a second light source, a second dichroic mirror and a sixth lens.The first light source and the second light source form a collimated light beam after being combined by the second dichroic mirror, and the collimated light beam is shaped by the sixth lens and then projected to an object plane through the first dichroic mirror.The application has the effects of simultaneously monitoring different types of neural signals or cell groups, distinguishing different states or functional modules of neurons, and improving the resolution and accuracy of data.

The application discloses an ASD child screening method based on fNIRS data quality improvement and empathy characteristics, and belongs to the technical field of brain imaging data processing and medical diagnosis. The method comprises the following steps: reading and verifying a `.nirs` data file; performing optical density conversion, motion artifact correction, band pass filtering and Beer-Lambert law conversion on light intensity data to obtain HbO / HbR / tHb concentration change data; extracting a time sequence based on a preset ROI, calculating ROI activation features and functional connection features; integrating the features into a unified feature package; adopting an IQR-count abnormal sample detection method to improve data quality, training an MLP classification model under the condition of each fold independent standardization, and outputting an ASD screening result. The method improves the accuracy, stability and reproducibility of fNIRS single-mode ASD child screening through fine abnormal value processing and empathy-emotion infection related neural feature extraction.

The application discloses a cognitive disorder screening method and device based on an XR eye tracker and near-infrared brain imaging, and the device comprises an extended reality scene generation module, an eye tracker data acquisition module, a near-infrared brain imaging module, a data analysis processing module and a cognitive disorder screening module. The extended reality scene generation module is used for generating and displaying a virtual reality scene and an augmented reality scene containing a cognitive task. The eye tracker data acquisition module is used for collecting eye movement data information sets of a user in real time when the user completes the cognitive task in the virtual reality scene and the augmented reality scene. The near-infrared brain imaging module is used for collecting blood oxygen information sets of the cerebral cortex of the user in real time when the user completes the cognitive task in the virtual reality scene and the augmented reality scene. The cognitive disorder screening module is used for performing cognitive disorder screening processing on evaluation process information, the eye movement data information sets and the blood oxygen information sets of the cerebral cortex, and obtaining cognitive disorder information of the user.

The application relates to the technical field of neuromodulation, in particular to a dynamic cognitive regulation system, which is suitable for dynamic cognitive regulation of different types of task paradigms. For dynamic cognitive regulation of each type of task paradigm, the system comprises the following modules: a cognitive function task module, which is used for establishing a mapping relationship between a task paradigm and a cognitive function and a mapping relationship between the cognitive function and a brain function area; a data analysis module, which analyzes cognitive function behavior data and cognitive function brain imaging data to obtain behavior indexes and brain imaging features; a regulation module, which performs cognitive regulation on a user according to regulation parameters set according to a cognitive aging risk probability judgment result of the user; and an evaluation module, which compares a current training result of the user with a historical training result to obtain an evaluation result, dynamically adjusts regulation parameters of a next round of cognitive regulation according to the evaluation result, and realizes dynamic monitoring and regulation of cognition.

This application relates to the field of neuromodulation technology, and in particular to a cognitive compensation assessment and regulation system. The cognitive compensation assessment system includes: a task module for distinguishing different types of cognitive compensation modes and triggering target task paradigms that activate different cognitive compensation modes; a data acquisition module for collecting behavioral data and brain imaging data of the user when performing the target task paradigm; a cognitive compensation calculation module for calculating the cognitive compensation effect exhibited by the user based on the collected behavioral data and brain imaging data to obtain a cognitive compensation index; and a cognitive compensation monitoring module for monitoring the cognitive compensation index, determining whether the target compensation effect has been triggered in the current target task paradigm, and assessing the user's cognitive compensation ability based on the user's behavioral data and the triggering status of the target compensation effect, thereby enabling adaptive regulation of the user's cognitive compensation ability.

The invention relates to a software-based method for activating and analyzing a neural network state of a subject for neurophysiological data analysis, pattern identification and characterization involving, the method comprising the steps of: (i) administering a resting-state condition during which the subject's brain activity is measured in the absence of rhythmic sensory stimulation or task; (ii) administering to the subject a sensory stimulation, possibly supplied with a cognitive task, selected from the group consisting of auditory stimulation, visual stimulation, haptic stimulation, electrical stimulation, and magnetic stimulation modalities such as transcranial alternating current stimulation, subauditory stimulation devices, functional electric stimulation, and skin-applied stimulation systems, or any combination thereof, at a frequency between at least 0.01 Hz and at most 120 Hz to induce rhythmic brain responses; (iii) measuring the subject's brain responses with one or more brain imaging or recording devices; (iv) analyzing the measured brain responses by performing a software analysis that generates either a brain topography or a network connectivity map in response to the sensory stimulation and a brain topography or connectivity map of the default mode network during the resting state; and (v) comparing the obtained brain topographies or functional connectivity maps to a database of normative data in order to identify abnormalities.

The application discloses a light field reconstruction brain image brain region boundary extraction method based on convex hull fitting, comprising the following steps: calculating the p percentile of a brain image and performing image cropping, contrast stretching, and Gaussian filter smoothing denoising; performing Canny edge detection on the filtered image to obtain a binary edge image; performing boundary enhancement and connection through inflation and closing operation, extracting all connected regions, and selecting the largest area contour as the contour of the brain region boundary; determining a reference point based on the contour of the brain region boundary, calculating the polar angle and distance of each point except the reference point and performing sorting, performing convex hull fitting through Graham Scan scanning based on the reference point and the sorted point set; converting the convex hull into a closed boundary region, and obtaining a mask image of the light field reconstruction brain image through a mask function; the application can accurately adapt to the special boundary form of the light field reconstruction image, does not need deep learning and training data, and the generated mask has high geometric consistency.

Diagnosis of dementia A method for diagnosing dementia subtypes is described. The method comprises obtaining brain imaging data relating to one or more patients, analysing the data using a deep learning model and classifying the one or more patients between a plurality of classes comprising a first class of patients having a first subtype of dementia and a second class of patients having a second subtype of dementia, using the deep learning model. The deep learning model has been trained using brain imaging data from patients, the brain imaging data comprising a first set of images showing evidence of temporo-parietal hypo-metabolism, and a second set of images showing evidence of hypo-metabolism in regions of the brain other than the temporal and preictal regions instead or in addition to the temporal and parietal regions, wherein the first set of images is labeled as associated with the first sub-type of dementia and the second set of images is labeled as associated with the second subtype of dementia. Related systems and methods are also described.

The application discloses a test model of near-infrared brain imaging equipment, which comprises a transmitting device, a receiving device, a light shield and a power device. The transmitting device comprises an upper shell for mounting a transmitter of an infrared imaging equipment, an upper POM inner core inlaid in the upper shell and an upper hollow light shield fixed at the lower part of the upper POM inner core, and the upper hollow light shield is provided with an upper light passing hole opposite to the transmitter. The receiving device comprises a lower shell for mounting a receiver of the infrared imaging equipment, a lower POM inner core inlaid in the lower shell and a lower hollow light shield fixed at the upper part of the lower POM inner core, and the receiver is arranged opposite to the transmitter, and the lower hollow light shield is provided with a lower light passing hole opposite to the transmitter. The light shield comprises a shield body and a first light passing hole arranged on the shield body, and the light shield reciprocatingly and linearly moves between the transmitting device and the receiving device, and the direction of the reciprocating and linear movement is perpendicular to the infrared light emitted by the transmitter. The power device drives the light shield to reciprocatingly and linearly move.

The application discloses a three-dimensional microwave brain imaging method and device based on image compression, which comprises the following steps: based on the microwave brain imaging, a three-dimensional antenna array is used to emit microwaves to detect the brain, a deep neural network is first trained to realize the encoding and decoding of the two-dimensional section image of the human brain dielectric constant, and then the three-dimensional brain model is represented by the hidden space parameters of the continuous section. In the three-dimensional brain imaging, given the measured microwave data, the objective function with the multilayer section hidden space parameters as the independent variables is minimized, the optimal hidden space parameters are solved, and finally the solved hidden space parameters are decoded into the three-dimensional human brain dielectric constant model. The application replaces the three-dimensional human brain represented by the point array with the hidden space parameters of the deep neural network, greatly reduces the imaging unknowns, and has higher calculation efficiency. The common structural features of the human brain can be included in the inversion by training the neural network, and the ill-posedness of the inverse problem solving is reduced.