125 results about "Cerebral part" patented technology

The invention discloses a multi-scale brain tumor segmentation method and system based on adaptive KAN, and a storage medium. The method comprises the following steps: preprocessing three-dimensional brain magnetic resonance imaging data; the preprocessed data are input into an encoder, the encoder comprises a plurality of levels, and each level executes convolution operation to extract local features, executes spatial KAN processing to extract spatial features and downsamples a feature map; the output of the encoder is input into a bottleneck layer, and the bottleneck layer captures a multi-scale global context by using a plurality of parallel expansion convolution branches; the output of the bottleneck layer is input into a decoder, the decoder comprises a plurality of stages, and each stage executes transposing a convolution up-sampling feature map, executes cross-scale gating processing to fuse encoder jump connection features and decoder features, and executes spatial KAN processing to optimize features; and the output of the decoder is input into the output module. According to the method, the problems of low calculation efficiency, poor tumor heterogeneity adaptation, insufficient multi-scale context capture and the like in the existing brain tumor segmentation can be effectively solved.

The invention discloses a cerebral apoplexy focus detection method and system, and belongs to the technical field of medical image detection. Extracting a fusion feature map of the brain image; for each region type, obtaining a representative feature which has the highest similarity with the feature at each pixel point position in the fused feature map in the class prototype set and carries a corresponding region type label, and further determining the region type to which each pixel point position in the fused feature map belongs so as to obtain a corresponding pseudo-label map; the class prototype set comprises representative features of different region types and is obtained in the training process of the system, and feature distribution of different region types in the memory bank is calculated through a Gaussian mixture model; for each region type, sampling is carried out based on feature distribution of the region type, and a plurality of representative features are obtained; the prototype-like set in the cerebral apoplexy detection method has real global context perception ability, can clearly distinguish the focus and various complex background structures, and can accurately realize cerebral apoplexy detection.

The invention relates to the field of small cerebral vessels, in particular to a medical image-based early feature analysis method and system for small cerebral vessels. The method comprises the following steps: acquiring a brain magnetic resonance image data set, preliminarily analyzing brain small vessel local features based on the brain magnetic resonance image data set, and generating a basic brain small vessel feature set; obtaining a clinical parameter set of the patient, analyzing the recessive influence factors according to the clinical parameter set of the patient, and generating a brain small vessel optimized feature set based on the basic brain small vessel feature set and in combination with the recessive influence factors; and performing visual fusion rendering according to the brain small vessel optimized feature set, and generating and outputting a record analysis log. In the process of early feature analysis of small cerebral vessels, doctors are assisted in accurately identifying the enlargement of the gaps around the vessels and simulators thereof, the misjudgment risk is effectively reduced, and the accuracy and reliability of early diagnosis of small cerebral vessel diseases are improved.

The invention relates to the technical field of neurosurgery navigation, in particular to a neurosurgery brain puncture path accurate planning method and system.The neurosurgery brain puncture path accurate planning method comprises the following steps that by obtaining a preoperative brain function area image and nerve fiber bundle data, a function area range and sensitivity are extracted, a focus and cranial entry point path set is constructed, and a path set is established; the method comprises the steps of analyzing the distance between a path and a functional area and a fiber bundle included angle, calculating a functional interaction risk, dividing path sections and calculating the distances to a blood vessel, a ventricle and the functional area, generating obstacle field intensity and calculating a gradient difference, constructing a risk map, scoring candidate paths, and screening an optimal path to generate a puncture result. The method comprises the following steps: extracting a brain function region range and a fiber bundle direction, introducing a function sensitivity parameter, improving tiny damage identification, calculating obstacle field intensity in a path segmentation manner, forming a gradient, dynamically identifying a high-risk region, grading and screening candidate paths by integrating risk factors, performing function protection and risk reduction, and improving path planning refinement and safety.

The invention discloses a perfusion imaging method and device for low-rotating-speed imaging equipment, a medium and a product, and relates to the field of medical image processing. The method comprises the following steps: acquiring plain-scan projection data and time sequence projection data of a brain interested body layer; determining a target time decay curve associated with the interested cerebral artery according to the time sequence projection data; determining a difference value between projection data corresponding to each scanning moment in the time sequence projection data and the plain scanning projection data, and taking the difference value as target projection data of the corresponding scanning moment; determining a target independent variable capable of enabling the target projection data and the forward model projection data to meet a difference minimization condition, and determining a perfusion parameter diagram combination based on the target independent variable; the forward model projection data is determined based on a target time decay curve and an independent variable, and the independent variable comprises a cerebral blood flow chart to be optimized and an average passing time chart. According to the invention, the accuracy of the perfusion parameter diagram combination determined based on the projection data acquired by the low-rotating-speed imaging equipment can be improved.

This invention discloses a data processing method and system based on the changing trends of image features, relating to the field of cerebral infarction early warning technology. The data processing method includes: feature extraction: processing image data and modal data separately using feature analysis methods to obtain image features, image feature change data, modal data features, modal data feature change data, and the regions where the features are located. In this invention, image data provides intuitive information about brain structure and lesions, while modal data supplements key features such as hemodynamics, brain tissue electrical activity, and electrical impedance from different physiological dimensions. TCD data can monitor blood flow velocity and vascular resistance in real time, BI data is sensitive to changes in pathological states such as cerebral edema, and EEG data reflects subtle changes in neuronal electrical activity. Through feature extraction and analysis, the combination of multi-source heterogeneous data achieves the correction of image feature changing trends, thereby ensuring the accuracy of data processing.

A method for determination of an indicator representative of a change in the brain caused by a demyelinating disease, the method including, for each region of interest of the brain, determining a regional coefficient of one of the following diffusion coefficients: the radial diffusion, the axial diffusion, the mean diffusion, the anisotropy fraction, or a combination of several of these coefficients, the regional coefficients being determined from a diffusion MRI image; determining a number of changed regions, for which a condition relating to the value of the regional diffusion coefficient of each region is satisfied; and determining the indicator in accordance with the number of changed regions.

The invention discloses a three-dimensional surgical risk model reconstruction method based on brain anatomy and a functional atlas, and the method comprises the steps: S1, carrying out the image processing and fine segmentation of a brain MRI image or a DICOM sequence image of a patient, and recognizing a plurality of anatomical structures; s2, establishing a multi-dimensional risk assessment model, and performing quantitative scoring on each brain region from four dimensions of functional importance, structural vulnerability, recovery potential and clinical significance; s3, constructing a continuous three-dimensional risk field based on the risk score, and realizing the propagation of the risk value in the brain tissue based on a Gaussian diffusion model; and S4, based on an improved path planning algorithm, searching an optimal operation path in the three-dimensional risk field to realize risk minimization. The invention further discloses a corresponding system, electronic equipment and a computer readable storage medium.

The invention discloses a cerebral infarction risk early warning method and system based on an image feature change trend, and relates to the technical field of cerebral infarction early warning. The cerebral infarction risk early warning method comprises the steps of feature extraction, wherein image data and modal data are processed through a feature analysis method, and image features, image feature change data, modal data features, modal data feature change data and regions where the features are located are obtained; the image data provides visual information of a brain structure and a focus, the modal data supplements key features such as hemodynamics, brain tissue electrical activity and electrical impedance from different physiological dimensions, the TCD data can monitor blood flow velocity and vascular resistance in real time, and the BI data is sensitive to change of pathological states such as encephaledema. The EEG data reflects the subtle change of the electrical activity of neurons, and the image feature change trend is corrected through feature extraction and analysis and combination of multi-source heterogeneous data, so that the accuracy of cerebral infarction risk early warning is ensured.

Provided are systems, methods, and devices for providing mediation of a traumatic brain injury. Systems may include an interface, processing devices, and a controller. The interface is configured to obtain measurements from a brain of a user with a traumatic brain injury. A first processing device is configured to generate multiple brain state parameters characterizing one or more features of a brain state of the user. A second processing device is configured to generate models of the brain of the user based on the plurality of brain state parameters and the plurality of measurements, and determine, using the models and training data comprising one or more mediation data points, a mediation procedure for reducing one or more symptoms of the traumatic brain injury. The mediation procedure is provided to one or more entities, and one or more control signals are generated by the controller based on the mediation procedure.

An artificial intelligence (Al) engine is trained on a plurality of annotated magnetic resonance (MR) images of a patient's brain. A plurality of MR images of a patient's head is provided. For each MR image in the plurality of provided MR images, the Al engine detects a plurality of edges of the brain and determine a biparietal diameter (BP) value, detects a plurality of frontal horn edges, and detects a plurality of occipital horn edges. A correction module determines that at least one detected edge is associated with a non -ventricular body and updates the edge to correspond to the applicable horn. The Al engine determines a frontal horn diameter (F) value, and a occipital horn diameter (O) value. An indication module provides an indication on abnormal dilation of the patient's brain ventricles based on a maximum F value, a maximum O value, and the maximum BP value.

The invention belongs to the technical field of medical instruments, and particularly discloses an intracranial pressure monitoring and external ventricular automatic drainage regulation and control device which comprises a sensing module, a lifting module and a control module. The sensing module comprises a pressure sensor and a blood pressure monitor, the pressure sensor is used for monitoring intracranial pressure data, and the blood pressure monitor is used for monitoring blood pressure data; the lifting module is provided with a mounting part, the mounting part is used for mounting a drainage bottle, and the drainage bottle is connected with the brain of a patient through a catheter; the control module is used for periodically executing the following operations: performing statistical analysis based on the intracranial pressure data and the blood pressure data to obtain multiple statistical values; and regulating and controlling the height of the mounting piece in the lifting module based on the plurality of statistical values. According to the device, monitoring data are obtained through the pressure sensor and the blood pressure monitor, statistical analysis and regulation are conducted through the control module, the state of a patient can be obtained in time, automatic regulation is conducted when the intracranial pressure of the patient is too low or too high, and the height of the drainage bottle is efficiently regulated.

The invention relates to the technical field of teaching models, in particular to a spliced mold capable of achieving lamplight demonstration of brain nerves and blood vessels and a control system. The system is composed of a plurality of physical modules which can be spliced and separated, and independent light-emitting units representing nerves and blood vessels are embedded in the modules. The system core comprises a monitoring module for monitoring the connection state of the module, a database for storing preset light sequences and voice explanation behaviors, an interaction interface for receiving user instructions and a control module serving as a control center. During working, the control module drives the corresponding light-emitting units to work in sequence according to a behavior instruction triggered by a user so as to dynamically simulate neural signals or blood flow, and can respond to splicing state changes of the modules in real time: when the modules are separated, internal light flow can be independently and continuously demonstrated; after the modules are spliced, the whole optical flow is recovered from the breakpoint. The system realizes unification of brain structure and function dynamic demonstration, local depth observation and overall process teaching.

The invention relates to a cerebral cortex metabolism visualization method and system. The method comprises the steps of obtaining a first functional image and a structure image of the brain of a target patient; based on the target neural network model, performing denoising processing on the first functional image to obtain a second functional image; wherein the target neural network model is obtained by training an initial neural network model based on a sample set, the sample set comprises multiple groups of samples, and each group of samples comprises a first functional image sample and a structure image sample of the brain of a sample patient; generating a three-dimensional grid model of the cerebral cortex according to the structure image; and mapping the metabolic information in the second functional image into the three-dimensional grid model, and visualizing the metabolic information in the three-dimensional grid model. By adopting the method, accurate correspondence and visual fusion expression of the brain anatomical structure information and metabolism information of the target patient can be realized, and the observation efficiency of a doctor is improved.

A system and method automatically detect, in MR images, WM lesions exhibiting a central vein sign. A set of MR images of a brain lesion is acquired, using images of the set as input to different ML algorithms. A first ML algorithm classifies inputted image(s) into first or second classes. The first class includes CVS+ / − and the second class CVSe lesions. A second ML algorithm classifies inputted image(s) into third or fourth classes. The third class includes CVS+ lesions and the fourth central vein sign− lesions. For each set, probability values are used that the set belongs to classes as inputs to a final classifier performing a final classification of the set into second, third, or fourth classes. For each class, the final classifier outputs final probability that the set belongs to the class. The second, third or fourth class with highest probability value is provided through an interface.

The invention provides an automatic alignment device used in transcranial magnetic stimulation (TMS) treatment, and relates to the field of transcranial magnetic stimulation. The method comprises the following steps: acquiring brain medical image data of a patient for segmentation and three-dimensional reconstruction, and generating a patient-specific brain three-dimensional virtual model containing a target stimulation target spot and key anatomical points around the target stimulation target spot; real-time pose data of the head of a patient is collected in real time, and spatial registration is carried out to establish an analytic coordinate system which comprises a three-dimensional virtual model and is synchronized with the spatial position of the real-time pose data of a physical state; and in combination with an electromagnetic field physical model of a TMS coil, current head pose data is calculated through a stimulation target mapping algorithm. And collecting current space pose data of the TMS coil in real time, comparing the current space pose data with the target space pose, resolving to obtain pose adjustment parameters, and driving a coil control mechanism to adjust the position and angle of the coil. The technical problems that due to unstable operation, a stimulation point deviates, and accurate positioning is difficult to achieve within a short time are solved.

The invention discloses a cerebrovascular segmentation method and device based on physical guidance and pyramid vision Transform, and relates to the field of medical image data, and the method comprises the steps: constructing a cerebrovascular segmentation model, and enabling loss functions used during training to comprise boundary intersection-to-union ratio loss, focus Tversky loss and Dice loss; the method comprises the following steps: acquiring an optical coherence tomography image of a brain to be processed, inputting the optical coherence tomography image into a trained cerebrovascular segmentation model, enabling the optical coherence tomography image to pass through an encoder module of pyramid vision Transform, and inputting an output feature of a first Transform encoding layer into a radial strength module to obtain a radial enhancement feature; wherein the output features of the second Transform coding layer, the third Transform coding layer and the fourth Transform coding layer are input into a deformable cross-scale fusion module to obtain enhanced fusion features, and the radial enhanced features and the enhanced fusion features are input into a boundary perception attention module to obtain a corresponding cerebrovascular prediction segmentation mask and a cerebrovascular prediction segmentation image. The problems of low segmentation accuracy and boundary precision in the prior art are solved.

The application provides a phototherapy device for treating brain-related diseases. The phototherapy device comprises a gas supply assembly, a head-wearing assembly and a first horn structure. The gas supply assembly comprises at least a gas supply pipe group. The head-wearing assembly comprises a shell and a light-emitting piece, the shell has a gas cavity in fluid communication with the gas supply pipe group, the gas supply pipe group is used for providing gas to the gas cavity, and the gas in the gas cavity is used for blowing to the head. The first horn structure is arranged at the gas outlet of the gas supply pipe group, and is used for diffusing the gas into the gas cavity via the first horn structure. The opening size of the first horn structure increases along the flow direction of the gas, and the cross-sectional area of the opening of the first horn structure is smaller than the cross-sectional area of the gas cavity. The phototherapy device can reduce the noise generated when the high-speed fluid transmitted from the gas supply pipe group enters the gas cavity with a relatively large cross-sectional area by arranging the first horn structure.

This invention discloses a method for measuring cranial thickness based on bioelectrical impedance analysis (BIA), comprising: dividing the target region into subdivisions using the finite element method (FEM) to establish a finite element model; acquiring surface voltage signals of the skull using a four-electrode method on a brain electrical impedance imaging platform; obtaining the conductivity distribution of each node of the triangular element by solving the inverse voltage problem; inputting the conductivity distribution into the finite element model and calculating the distance between the node with the largest resistivity change and the corresponding boundary voltage node by solving the forward problem, thus obtaining the skull width at a set of signal locations; measuring the node voltages and calculating the corresponding skull thickness using a sixteen-electrode cyclic excitation method; and finally, assembling all node voltages and skull thicknesses into a plane to obtain the overall skull thickness. This invention designs a method for measuring cranial thickness based on bioelectrical impedance analysis (BIA), providing an accurate method for calculating cranial thickness.

The application relates to the field of medical instruments, and provides a brain operation path guiding system, which comprises an operation instrument, a face scanning three-dimensional camera, a positioning three-dimensional camera and a processor. The application determines a first pose conversion relationship between an operation instrument positioning code and the operation instrument, a second pose conversion relationship between the face scanning three-dimensional camera and a camera positioning code, a third pose conversion relationship between the positioning three-dimensional camera and the camera positioning code, and a fourth pose conversion relationship between the positioning three-dimensional camera and the operation instrument positioning code, carries out three-dimensional reconstruction based on an MRI image of a patient to obtain an MRI reconstruction model comprising a three-dimensional operation path, and determines a position and an angle offset between the operation instrument and the three-dimensional operation path according to the first, second, third and fourth pose conversion relationships, the MRI reconstruction model and a three-dimensional point cloud model of a patient face transmitted by the face scanning three-dimensional camera, so that the accuracy of an operation position and an operation angle is improved, and the operation risk is reduced.

The utility model discloses a fixing band for PET / CT brain examination, which is characterized in that a band body comprises a fixed end and a movable adjusting end, two opposite sides of a pillow body are respectively provided with a fixed connecting piece and an adjusting opening, a mounting cavity communicated with the adjusting opening is arranged in the pillow body, a rotary adjusting piece is rotatably arranged in the mounting cavity, and the movable adjusting end is connected with the rotary adjusting piece. The movable adjusting end of the belt body extends into the mounting cavity from the adjusting opening and is wound on the rotary adjusting piece, the driving end of the rotary adjusting piece extends out of the end of the pillow body and is connected with a rotary operating piece, the rotary adjusting piece is driven by the rotary operating piece to rotate in different directions so as to tighten or loosen the belt body, and a locking assembly is arranged on the pillow body. And a locking structure is arranged on the rotary adjusting piece. According to the fixing band for PET / CT brain examination, the rotary adjusting piece can be driven to rotate through the rotary operating piece, so that the band body can be rolled or loosened, and the head of an examiner can be fixed to the pillow body.

The invention provides a method for quantifying a water content ratio, which comprises the following steps of: scanning a brain by using first energy and second energy through dual-energy CT (Computed Tomography) equipment to generate plain scanning data of each voxel; setting the three substances of the dual-energy tomography three-substance separation mathematical model as water, grey matter and white matter; processing the plain scanning data of each voxel by using the dual-energy tomography three-substance separation mathematical model to obtain enhanced data of each voxel; and calculating the water content percentage of each voxel according to the enhancement data of each voxel. The method for quantifying the water content can quantify the water content of the encephaledema tissue of the acute stroke patient, and further quantify the edema proportion of the encephaledema tissue. The invention further provides a water content ratio quantifying device, a tomography system and a storage medium which relate to the method.

The application relates to an extracorporeal circulation detection device. The method comprises a control module, an impedance detection module and a temperature detection module, the control module being connected with the impedance detection module and the temperature detection module; the impedance detection module is arranged at a plurality of preset positions of the head of a to-be-detected object, is used for detecting impedance data of the brain of the to-be-detected object in real time, and is connected with the control module; the temperature detection module is arranged at a plurality of preset positions of the body of the to-be-detected object, is used for detecting body temperature data of the to-be-detected object in real time, and is connected with the control module; the control module is connected with an extracorporeal circulation device, is used for acquiring real-time setting temperature of the extracorporeal circulation device, and determines the state of the extracorporeal circulation device when the extracorporeal circulation device performs extracorporeal circulation on the to-be-detected object according to the impedance data, the body temperature data and the real-time setting temperature. The method can comprehensively and efficiently detect the state of the to-be-detected object in extracorporeal circulation.

To enable users to easily identify potential placement locations for intravascular electrodes that are close to the source of the nerve activity being measured. [Solution] The medical image processing apparatus according to the embodiment comprises a vessel diameter image generation unit, a distance image generation unit, a device implantation position candidate identification unit, and a display control unit. The vessel diameter image generation unit generates a vessel diameter image representing the size of the vessel diameter inside the brain from a cerebral vessel image taken of the blood vessels of the brain. The distance image generation unit identifies a target position corresponding to the neural activity that is the target of measurement inside the brain, based on an image relating to at least one of the functional areas of the brain and the arrangement of nerves inside the brain, and generates a distance image showing the distance to the identified target position. The device implantation position candidate identification unit identifies a position on the vessel where both the vessel diameter and the distance from the target position satisfy a specified criterion, based on the vessel diameter image and the distance image, as a candidate for device implantation position. The display control unit highlights the identified implantation position candidate on an image representing the brain.

The invention belongs to the technical field of medical image processing, provides a medical image-based computer-aided diagnosis method and system, and solves the problem of insufficient computer-aided diagnosis. The method comprises the following steps: collecting a brain diffusion tensor image of a target object and a surface electromyogram signal of an associated muscle group; converting the image into Riemannian manifold data through tensor resolving and symmetric positive definite matrix mapping; extracting a Hurst index of the electromyographic signal based on remarking range analysis, and generating a motion feature vector; using Riemannian logarithm mapping and canonical correlation analysis to project manifold data and motion features to a correlation space, and extracting a maximum correlation component to generate a coupling feature vector; determining a reconstruction site through Riemannian index mapping, and calculating a geodesic line length between the reconstruction site and the reference state point to obtain a deviation value; and quantitatively judging the nerve remodeling degree and the motor function level of the stroke patient according to the deviation value. According to the application, accurate quantitative evaluation of the stroke nerve remodeling and motion recovery state is realized.

Some methods comprise, for each of one or more lesions of a patients brain, from data taken at first and second times, determining two or more lesion characteristics including a lesion's volume change and whether the lesion moved toward a center of the brain. Some methods comprise, for each lesion, determining whether one or more criteria are satisfied, including a volume-and-displacement-based criterion that is satisfied when the change in the volume of the lesion is less than zero and the lesion moved toward the brain's center or the change in the volume of the lesion is greater than zero and the lesion did not move toward the brain's center. Some methods comprise characterizing whether the patient has multiple sclerosis and / or the progression, regression, or stability of multiple sclerosis based at least in part on the assessment of the one or more criteria for each of the lesion(s).

The invention discloses an improvement method of a rat cerebral ischemia reperfusion model, which comprises the following steps: S1, anesthetizing a rat, fixing, and separating and exposing an external carotid artery (ECA), a common carotid artery (CCA) and an internal carotid artery (ICA); s2, ligating one part of the trunk of the external carotid artery (ECA) close to the bifurcation of the trunk and the common carotid artery (CCA) to realize temporary blocking of the ECA; s3, temporarily blocking reverse blood flow at a telecentric end vascular clamp, close to the skull base as much as possible, of the internal carotid artery (ICA); the proximal end, far away from the bifurcation, of the trunk of the common carotid artery (CCA) is firmly bound through a 4-0 silk thread, and blood supply of the CCA to the brain is permanently blocked. A 4-0-degree silk thread is threaded at the position 3-5 mm away from the telecentric end of the ligation point, and a slipknot is tied to prepare a fixing thread bolt. According to the method, temporary ligation is carried out on a single part of the external carotid artery, and instant knot loosening is carried out after operation, so that partial blood supply of the ocular artery is recovered, the problem of retinal atrophy caused by long-term blocking of the external carotid artery of a traditional MCAO model is thoroughly solved, and model pathological correlation and animal welfare are considered.

Cerebral autoregulation is a physiological process that ensures stable and adequate blood flow to the brain, despite fluctuations in systemic blood pressure. Non-invasive measurement of cerebral blood flow and related parameters is complex and challenging, often requiring an invasive arterial line (A-line). Using concurrent PPG and ECG signals as inputs to one or more machine learning models, methods and systems non-invasively determine blood pressure (BP) output, including waveform morphology, MAP trending, and predicted BP in mmHg, and real-time quality metrics associated therewith. Based on the BP output, along with other inputs, non-invasive monitoring of cerebral autoregulation is provided.

Provided is a program capable of acquiring increase information related to the presence or absence of an increase in cerebral aneurysm, on the basis of a Magnetic Resonance Angiography (MRA) image of a brain. A computer acquires MRA images of the brain. If MRA images of a brain have been input, the computer inputs the acquired MRA images of the brain to a learning model that outputs increase information related to the presence or absence of an increase in cerebral aneurysm, and the computer thereby acquires increase information related to the presence or absence of an increase in a cerebral aneurysm in the input MRA images.

The invention provides a cerebral apoplexy postoperative care risk early warning method and system fused with a brain image, and the method comprises the steps: improving the prediction precision through multi-modal data fusion, and integrating clinical physiological features, focus function influence points and brain connection group disconnection features to construct an initial data set; learning the importance of each feature by using the primary model, adjusting the weight of the brain function map, and optimizing the focus influence integral to enhance the representation ability; for a sample imbalance problem, generating a synthetic sample based on an importance coefficient according to a local density and a weighted distance, and realizing minority class expansion; and training a risk early warning model based on the balanced data set, inputting a new patient by adopting the same feature extraction process, outputting a personalized postoperative care risk level, and realizing an intelligent assessment closed loop from image anatomy to a functional network.