41 results about "Fiber tract" patented technology

The invention discloses a brain disease classification method and system. Precise diagnosis is realized through multi-modal data fusion and dynamic modeling. The method comprises the following steps: collecting multi-modal brain image information and cognitive behavior information of a user; performing dynamic function connection analysis on the resting state functional magnetic resonance time sequence signal to obtain a time-varying brain network feature matrix, and performing white matter fiber bundle topology reconstruction on a structure connection matrix; constructing a four-dimensional correlation tensor by using the time-varying network features, the structural connection weights and the anatomical features through a neurodynamic model; performing multi-task learning on the four-dimensional correlation tensor based on a time-varying graph neural network model, and outputting a quantitative diagnosis result; and finally generating a clinical classification report integrating the individualized brain network remodeling target, the disease progress risk layering and the treatment response prediction. By dynamically fusing the structure and functional features, comprehensive characterization of the pathological mechanism of the brain disease is realized, and decision support with both accuracy and interpretation is provided for clinical diagnosis.

The invention discloses a tumor space-occupying brain network neural image alignment method based on multi-modal fusion, and belongs to the technical field of medical image processing and artificial intelligence crossing. The method comprises the following core steps of multi-modal image heterogeneous feature decoupling, tumor occupation deformation field modeling, functional network topological structure maintenance, cross-modal feature adversarial alignment, dynamic deformation constraint optimization and clinical interpretability verification, and construction of a three-dimensional non-rigid registration network based on a double attention mechanism. And differential homeomorphic mapping of a tumor focus area and normal brain tissue is realized through the cascaded spatial transformation module. Aiming at the problems of insufficient multi-modal feature alignment and brain network topology distortion in the prior art, the invention provides a function connection constrained cross-modal fusion strategy, a graph convolution network is adopted to encode resting state function connection features, and network node displacement caused by tumor occupation is dynamically corrected in combination with deformable convolution and a bidirectional feature competition mechanism; a space consistency loss function based on white matter fiber bundle tracing is designed, and through diffusion tensor imaging feature guide structure-function bimodal joint optimization, the problems of insufficient registration precision in a focus area and whole brain network connection distortion of a traditional method are solved. Experiments show that the registration precision of the method in glioma cases reaches 0.82 mm and is improved by 37% compared with that of a traditional method, and dissection-function consistency of functional network reconstruction around tumors is remarkably improved.

The invention discloses a white matter fiber bundle structure-function connection coupling method based on a distance function. The method comprises the steps that brain imaging data are collected and preprocessed; extracting white matter fiber bundle structure attributes and function signals of the preprocessed brain imaging data; constructing a structure connection matrix and an individualized function connection matrix according to the white matter fiber bundle structure attributes and the function signals; measuring the connection weight similarity between corresponding columns of the structure connection matrix and the function connection matrix through a distance function, and carrying out white matter fiber bundle structure-function connection coupling according to the connection weight similarity; through the method, the relationship of the white matter fiber bundle structure and function of the brain can be quantified, and the method is suitable for brain structure and function analysis based on the white matter fiber bundle and research on brain development and mental diseases.

The invention provides an Alzheimer's disease virtual injury judgment method based on a brain dynamics model, and the method comprises the steps: S1, obtaining a structural magnetic resonance image and a functional magnetic resonance image of a subject, and carrying out the preprocessing, and obtaining the preprocessed data; s2, calculating topological characteristic indexes of the structural network; s3, drawing a required topological feature profile map; s4, clustering is carried out on the topological feature profile map; s5, constructing a whole brain dynamic model for each subject; s6, constructing a node disturbance model of each subject, and analyzing a relationship among a structural network topology characteristic index, a cortical hierarchy gradient index and a whole brain dynamic index; s7, according to the cortex thickness and the cortex volume of the subject, in combination with the whole brain dynamics model, judging the influence of local brain region atrophy on whole brain metastable state dynamics; and S8, judging the influence of white matter fiber bundle connection disconnection on the whole brain metastable state dynamics. The invention provides a brain network dynamics model modeling method for different structure damage effects.

An apparatus includes an input unit, a processing unit, and an output unit. The input unit is configured to provide the processing unit with at least one diffusion magnetic resonance imaging dMRI image of a patient's brain. The processing unit is configured to: 1) determine an estimate of an orientation of neurons at each voxel in the dMRI image; 2) determine a plurality of fiber tracts in the at least one dMRI image; 3) select a plurality of voxels along at least one fiber tract of the plurality of fiber tracts; and 4) determine a neurological disease classification.

The invention relates to the technical field of stereotactic surgery, and discloses a neurosurgery stereotactic surgery positioning system based on multi-modal image fusion, which comprises a multi-modal image acquisition module, an intelligent registration fusion module, a three-dimensional modeling module, a surgery navigation engine, an augmented reality interface and a dynamic calibration module, a cross-modal elastic registration module is arranged, when multi-modal image fusion is carried out, the spatial matching degree of a functional image and a structural image is detected in real time through a nonlinear deformation compensation algorithm, and when registration deviation exists between white matter fiber bundles and tumor boundaries, an elastic deformation compensation field is dynamically generated by a system, so that the positioning accuracy of a neural functional area is improved; and by arranging the dynamic drift correction module, the brain tissue displacement change is perceived in real time based on laser surface scanning during deep target navigation, precise correction of the pose of the surgical instrument is realized, and the positioning reliability of the deep target is ensured.

The invention relates to a mechanical property prediction method for a woven composite material structure, and the method comprises the steps: obtaining a microscopic CT image of the woven composite material structure; carrying out image preprocessing on the CT image; segmenting a fiber bundle in the preprocessed image to obtain a segmented fiber bundle image; extracting a fiber bundle trend center line from the segmented fiber bundle image; establishing a macroscopic geometric model of the woven composite material structure, and performing unit grid division on the geometric model; establishing a relation between a fiber bundle trend center line and a geometric model unit; calculating mechanical property parameters of each unit one by one; and calculating the macromechanical response of the composite material structure. According to the method for predicting the mechanical property of the woven composite material structure, the grid division independent of the microstructure characteristics is adopted, so that the modeling efficiency can be improved, the modeling difficulty can be reduced, and the method is easy to implement.

The invention discloses a brain connection coupling analysis method based on grey matter morphological similarity-white matter fiber bundles, relates to the technical field of neuropsychiatric imaging, and has the technical key points that the method can be used for analyzing grey matter-white matter brain connection group coupling modes of the whole brain level, the level in brain network communities and the level between the brain network communities; the integration characteristics of structural tissues of the brain on different scales can be understood; the reliability of statistical analysis is improved by adopting a spatial autocorrelation correction method; based on a specific machine learning fusion model, the clinical application value of the model is verified.

Systems and methods for configuring neurostimulation systems to identify optimal therapies for use in a patient. Positional data for a lead implanted in the patient and anatomical data are obtained. Non-linear response structures are identified in the patient, and therapy metrics are generated using non-linear functions of the quantity of volume segments in the non-linear response structures that would be activated by a given therapy configuration including a combination of current fractionalization and current amplitude.

The application discloses a fiber bundle automatic segmentation and quantitative labeling method for white matter abnormalities of Parkinson's disease, and belongs to the technical field of medical image processing. The application solves the problem that the existing technology relies on manual delineation or traditional machine learning methods for white matter abnormality detection, and has the problems of low efficiency and strong subjectivity. By setting a first threshold value and a second threshold value, not only can the abnormal fiber bundle be identified, but also the required threshold range can be selected according to different research purposes and clinical needs, so that reliable judgment results can be provided in both diagnosis and early screening. If both threshold values are selected, the method can comprehensively judge each parameter of each fiber bundle, so as to more accurately identify the white matter abnormal fiber bundle of the Parkinson's disease patient, improve the accuracy of the fiber bundle labeling result of the white matter abnormalities of Parkinson's disease, realize the function of high-precision positioning of the white matter abnormal fiber bundle of Parkinson's disease, and provide stronger support for clinical diagnosis.

The invention discloses an accurate positioning system based on multi-modal image fusion, and the system comprises a multi-modal image collection module which synchronously collects an MRI structure image, an fMRI function image and a DTI white matter fiber bundle image of the brain of a patient; the image preprocessing module is connected with the acquisition module and is used for de-noising, registering and standardizing the multi-modal image data to generate fused image data under a unified coordinate system; the target analysis module is connected with the preprocessing module and calculates initial coordinates of the target based on the fused data; the dynamic correction module is connected with the analysis module, monitors the head movement in real time and dynamically corrects the target position; and the target spot guiding terminal is connected with the correction module and controls the mechanical arm to accurately position according to the corrected coordinates. According to the system, the transcranial magnetic stimulation target spot positioning accuracy and the personalized adaptive capacity can be remarkably improved, the problems that a traditional method depends on experience and the single-mode image accuracy is insufficient are solved, and meanwhile the positioning stability and the effect evaluability in treatment are ensured.

Exemplary system, method and computer arrangement for determining rotational invariants, fiber orientations, and scalar parameters of fiber tracts (e.g., compartment fractions, which can relate to intra / extra-cellular space volumes; compartment diffusivities; relaxation rates; exchange rates between compartments; characteristics of structural disorder such as axonal beading) from a general diffusion MRI acquisition is described. For example, gradient directions may not necessarily be arranged in so-called shells, and an acquisition may vary spatially. Furthermore, each acquisition can be undersampled in the k-space. A procedure can also be included for receiving information related to the at least one image. Another procedure can be provided for decoupling tissue and protocol parameters based on a singular value decomposition. A further procedure can be provided for grouping singular vectors into multiplets based on symmetries. Still further procedures can be provided for forming rotational invariants and / or for a parameter estimation.

This invention provides a parameter conversion method and system for multimodal brain network maps. The method includes: acquiring and comparing multiple source brain regions and multiple target brain regions of a single subject; constructing a set of overlapping brain regions between each target brain region and the source brain region; and statistically analyzing the number of white matter fiber tracts and brain functional connectivity coefficients between each set of overlapping brain regions. Based on this, the remapping coefficients of the white matter fiber brain network and the brain functional connectivity coefficient brain network are calculated respectively. The method also includes: acquiring and statistically analyzing the set of overlapping brain regions between the target brain regions and the source brain regions of multiple subjects, as well as the corresponding number of white matter fiber tracts and brain functional connectivity coefficients; calculating the variance of the brain connectivity strength of the first experimental group and the first control group under the source map, and the second experimental group and the second control group under the target map; and weighting and summing the source brain connectivity statistics between the overlapping brain region sets using influence weights to obtain the target brain connectivity statistics between the target brain regions.

The application discloses a brain region homology cross-species comparison method based on gray matter brain regions and fiber bundles, which comprises the following steps: acquiring cross-species brain image data and performing pretreatment; extracting a region of interest from a standard template and performing brain region division to obtain a region of interest division result of different species; using whole brain-based probabilistic fiber tracking to construct connection fingerprints of each subregion of the region of interest and the gray matter brain region; using voxel-based probabilistic fiber tracking to construct connection fingerprints of each subregion of the region of interest and the fiber bundle; obtaining effective gray matter brain region connection fingerprints and fiber bundle connection fingerprints within a species at a group level; calculating similarity or difference between each subregion of the region of interest of different species based on the connection fingerprints to obtain cross-species homology scores; and verifying the method based on the consistency of the homologous subregion to the whole brain functional connection mode. From the perspective of brain mapping and evolution, the method provides a new idea and a new method for cross-species homology comparison of specific brain region subregions by taking the gray matter brain region and the subcortical fiber bundle as feature inputs.

A computer-implemented method for performing diffusion tractography of a subject's brain, includes generating, by a computer system that includes at least one processor in communication with at least one memory system, for each canonical fiber tract bundle in a canonical fiber tract model, subject specific regions of interest (ROIs), detecting, by the computer system, a canonical set of fiber tracts in magnetic resonance (MR) data of the subject's brain based on the canonical fiber tract model and the subject specific ROIs, and generating, by the computing system, a subject-specific brain map comprising the canonical set of fiber tracts detected in the MR data of the subject's brain.

Provided is a technique capable of evaluating cross fibers in a fiber bundle. The method of the present invention comprises the following steps: (a) acquiring a brightness image of a fiber bundle; (b) generating a two-dimensional power spectrum image by performing a two-dimensional FFT analysis on the luminance image data; (c) generating a corrected power spectrum image by performing mask processing on the two-dimensional power spectrum image to remove a mask region corresponding to a luminance image component in which the angle of intersection with the horizontal direction of the luminance image is equal to or less than an angle threshold; and (d) generating a modified luminance image by performing an inverse FFT analysis on the modified power spectrum image.

1. The name of the design product: surgical planning graphical user interface for electronic device. 2. The use of the design product: an electronic device, such as a medical instrument device. 3. The design points of the design product: in the graphical user interface. 4. The picture or photo that best shows the design points: design 1 front view. 5. Design 1 is designated as the basic design. 6. The use of the graphical user interface: the graphical user interface can be used in a medical instrument device, such as with laser treatment, to design a surgical plan on a sequence of images. In the design 5 front view, move the controller (such as a mouse, touch pen, etc.) into the box in the lower right to display design 5 change state figure 1. In the design 6 front view, click the "surgical view" button in the lower right to display design 6 change state figure. In the design 7 front view, click the "sequence registration" button in the upper right to display design 7 change state figure. In the design 8 front view, click the "fusion" button on the right to display design 8 change state figure. In the design 9 front view, click the "fusion" button on the right to display design 9 change state figure 1, and in design 9 change state figure 1, click the "3D model display" button on the right to display design 9 change state figure 2. In the design 10 front view, click the "fusion" button on the right to display design 10 change state figure 1, and in design 10 change state figure 1, click the "3D model display" button on the right to display design 10 change state figure 2, and in design 10 change state figure 2, click the "fiber tract reconstruction" button on the right to display design 10 change state figure 3.

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.

The application relates to the field of stereotactic surgery technology, and discloses a neurosurgical stereotactic surgery positioning system based on multi-modal image fusion, which comprises a multi-modal image acquisition module, an intelligent registration and fusion module, a three-dimensional modeling module, a surgery navigation engine, an augmented reality interface and a dynamic calibration module; through the setting of the cross-modal elastic registration module, when the multi-modal image fusion is carried out, the spatial matching degree of functional images and structural images is detected in real time through a nonlinear deformation compensation algorithm; when there is a registration deviation between the white matter fiber bundle and the tumor boundary, the system dynamically generates an elastic deformation compensation field, the positioning accuracy of the functional area is improved, and the risk of functional area cutting is reduced; through the setting of the dynamic drift correction module, when deep target point navigation is carried out, the brain tissue displacement change is sensed in real time based on laser surface scanning, the accurate correction of the position and posture of a surgical instrument is realized, and the reliability of deep target point positioning is ensured.

Abnormal activity in the brain can be detected by identifying changes in tissue excitability measured in response to stimulation of fiber tracts such as the corpus callosum. A stimulating electrode contact can apply a stimulation to the fiber tract, which can have one or more terminals to a cortex of a patient's brain, and a recording electrode contact positioned in the fiber tract and / or the cortex to record a tissue excitability response to the stimulation. A controller can receive the tissue excitability response from the at least one recording electrode, identify a parameter of the tissue excitability response, and predict the abnormal activity in the patient's brain based on the parameter being different from a baseline for the parameter. When an abnormal activity is predicted the patient can be alerted to start a therapy and / or a therapy can be applied in closed loop manner by a connected therapy device.

This invention discloses a method and system for neural fiber tract clustering and segmentation based on diffuse hypervoxels, relating to the fields of medical image analysis and artificial intelligence. The method includes: receiving and preprocessing three-dimensional brain magnetic resonance imaging (MRI) data; establishing a population-matched personalized MRI brain template using an iterative registration method; constructing a diffusion-weighted undirected graph and segmenting diffuse hypervoxels based on diffusion geodesic distance; clustering fiber tracts based on the maximum clusters of the neural fiber connectivity graph of the diffuse hypervoxels; registering the diffuse hypervoxels to an individual space and using the maximum clusters to achieve personalized fiber tract segmentation; constructing a center curve for the fiber tract clusters and mapping diffusion features to this curve; establishing a statistical analysis method for the center curve based on permutation tests and building a machine learning classification model.

This invention relates to a carotid artery plaque analysis device based on magnetic resonance imaging (MRI). Breaking with conventional research focusing solely on carotid artery plaques, this device explores the relationship between plaques and brain structure. By analyzing early brain changes, particularly brain volume data, functional network topology data, and white matter fiber tract data, a device for analyzing carotid artery plaque properties is constructed. This device applies theoretical research to practical applications, qualitatively analyzing carotid artery plaque properties to determine whether plaques are warning signs with a high probability of rupture or safe plaques with a low probability of rupture. This analysis device can be used to predict and prevent cerebral ischemia. This device can be used for clinical early warning and preventive measures, significantly improving diagnostic accuracy and saving lives.

Methods, compositions and kits useful in the detection, assessment, diagnosis, prognosis and / or treatment of brain injuries, especially mild traumatic brain injury (mTBI) or concussion, are based upon detection of changes in levels of certain protein biomarkers in a subject undergoing testing, or upon detection of changes in levels of certain protein biomarkers in conjunction with neuroimaging analyses to detect changes in vascular or blood brain barrier (BBB) permeability in the brain, or to detect damage to fiber tracts in the brain, in which changes in biomarker levels correlate with detection of changes in BBB permeability or in brain fiber tract or white matter damage in a subject with brain injury such as mTBI or concussion.

The invention discloses a brain-spine DTI fiber bundle extraction system and method based on clustering and overlapping rate denoising. The method comprises the following steps: carrying out preprocessing including denoising, Gibbs ringing correction and eddy current correction and normalization on a brain-spine DTI image; n4 deviation field normalization processing is carried out on the individual T1 structure image, segmentation is carried out according to anatomical sites, and joint registration is carried out on the spinal cord T1 image and a standard template; tracking brain-spine combined fiber bundles of interest for the individual; clustering the interested fiber bundles in the individual space; the mapping image of the individual space fiber bundle is converted to a standard space, and the mean value of all individual images is taken to obtain an overlapping graph and then de-noising is carried out. According to the method, standardized preprocessing and fiber bundle extraction and analysis processes are provided for brain-spine synchronous DTI image data, the interested fiber bundles in the DTI images of individuals can be stably and truly extracted, and the method has the remarkable advantages of being sufficient in denoising, stable and reliable in effect and the like.

The invention belongs to the technical field of medical image data processing, and particularly relates to a cerebral hemorrhage patient white matter fiber bundle reconstruction method based on a CT image. According to the method, paired CT and dMRI data are utilized to make training data, then a segmentation model and a generative model are adopted to construct a reconstruction network, a trained reconstruction network is obtained after training, and white matter fiber bundle reconstruction is performed by utilizing the trained reconstruction network. According to the cerebral hemorrhage patient white matter fiber bundle reconstruction method based on the CT image, white matter fiber bundle reconstruction can be directly carried out on the CT image without depending on dMRI, and a certain guiding effect on clinical cerebral hemorrhage diagnosis and treatment schemes is achieved.

Exemplary system, method and computer arrangement for determining rotational invariants, fiber orientations, and scalar parameters of fiber tracts (e.g., compartment fractions, which can relate to intra / extra-cellular space volumes; compartment diffusivities; relaxation rates; exchange rates between compartments; characteristics of structural disorder such as axonal beading) from a general diffusion MRI acquisition is described. For example, gradient directions may not necessarily be arranged in so-called shells, and an acquisition may vary spatially. Furthermore, each acquisition can be undersampled in the k-space. A procedure can also be included for receiving information related to the at least one image. Another procedure can be provided for decoupling tissue and protocol parameters based on a singular value decomposition. A further procedure can be provided for grouping singular vectors into multiplets based on symmetries. Still further procedures can be provided for forming rotational invariants and / or for a parameter estimation.

The invention relates to a nerve fiber bundle reconstruction method and system based on streamline tracking. The method comprises the following steps: extracting a diffusion weighting factor and a diffusion gradient vector of a diffusion weighted image and carrying out preprocessing; constructing a linear equation set for diffusion tensor matrix calculation; solving a diffusion tensor matrix through a non-negatively constrained iterative reweighted least square method; carrying out diagonalization processing on the diffusion tensor matrix, and solving a characteristic value and a characteristic vector; according to the solved characteristic value, calculating the fractional anisotropy of each voxel in the diffusion weighted image, and according to the calculated fractional anisotropy, determining an initial threshold value and an end threshold value of streamline tracking; according to the solved feature vector, the initial threshold value and the termination threshold value, streamline tracking is carried out through an adaptive step length Runge-Kutta integration method; and reconstructing the nerve fiber bundle according to a tracking result. According to the invention, more accurate and efficient nerve fiber bundle reconstruction can be realized.

The invention discloses a fiber bundle automatic segmentation and quantitative labeling method for white matter abnormality of Parkinson's disease, and belongs to the technical field of medical image processing. The problems that in the prior art, white matter anomaly detection depends on manual sketching or a traditional machine learning method, efficiency is low, and subjectivity is high are solved, by setting the first threshold value and the second threshold value, the abnormal fiber bundles can be recognized, the needed threshold value range can be selected according to different research purposes and clinical requirements, and the detection accuracy is improved. Therefore, reliable judgment results can be provided after definite diagnosis and in early screening; if the two thresholds are selected to be used at the same time, the method can comprehensively judge each parameter of each fiber bundle, so that the white matter abnormal fiber bundle of the Parkinson's disease patient can be more accurately identified, the accuracy of the marking result of the white matter abnormal fiber bundle of the Parkinson's disease is improved, and the accuracy of the marking result of the Parkinson's disease white matter abnormal fiber bundle is improved. The high-precision positioning function of the fiber bundle for white matter abnormality of the Parkinson's disease is achieved, and more powerful support is provided for clinical diagnosis.

The present invention discloses a disease classification system based on deep learning and fiber bundle spatial statistical analysis, including: an acquisition module, which acquires a brain image to be classified; a preprocessing module, which is configured to: preprocess the brain image to be classified; an image generation module, which generates anisotropic fractional images, average diffusion rate images and radial diffusion rate images based on the preprocessed brain image; a voxel extraction module, which extracts a first voxel matrix from the anisotropic fractional image; extracts a second voxel matrix from the average diffusion rate image; extracts a third voxel matrix from the radial diffusion rate image; splices the three matrices to obtain a spliced ​​matrix; and a classification module, which inputs the spliced ​​matrix into a trained deep learning classification model to obtain a disease classification result. Voxels are extracted in blocks to prevent information loss, and after splicing, they are classified using a deep learning model, which has a good classification accuracy.

A computer-implemented method for interventional planned brain mapping and target recognition using magnetic resonance imaging (MRI) includes receiving, by a computing system, MR data from an MRI system, the computing system including at least one processor in communication with at least one storage system, and the computing system communicates to receive data acquired using the MRI system. The method further includes analyzing the received MR data to monitor and identify motion in real time, determining an available MR dataset from the acquired MR data based on the identified motion, generating a map of the subject's brain based on the available MR dataset, and identifying a subcorpus callosum of the subject's brain based on the map of the subject's brain, sCC) in the region. The target location may be a point converged by a plurality of fiber bundles of the SCC region. The method may further include generating a report indicating the target location.