50 results about "Brain hemorrhages" patented technology

An ultrasound catheter with fluid delivery lumens, fluid evacuation lumens and a light source is used for the treatment of intracerebral hemorrhages. After the catheter is inserted into a blood clot in the brain, a lytic drug can be delivered to the blood clot via the fluid delivery lumens while applying ultrasonic energy to the treatment site. As the blood clot is dissolved, the liquefied blood clot can be removed by evacuation through the fluid evacuation lumens.

The invention discloses a cerebral hematoma segmentation method and system based on deep learning. The method comprises the following steps: constructing a neural network model, the neural network model comprising a plurality of image information compression modules which are connected in sequence and a plurality of image information fusion modules which are connected in sequence, wherein the image information compression module comprises a first self-attention convolution unit, a second self-attention convolution unit and a pooling layer which are connected in sequence, and the image information fusion module comprises an up-sampling unit, a feature map splicing unit and a third self-attention convolution unit which are connected in sequence; obtaining a brain CT sample image; training the neural network model by taking the brain CT sample image as input and the bleeding condition of each pixel point in the brain CT sample image as a label; and adopting the trained neural network model to perform cerebral hemorrhage identification on the to-be-segmented brain CT image. According to the method, the bleeding area in the brain CT image can be accurately and efficiently segmented.

The invention discloses a craniocerebral operation training simulation model comprising a simulation skull bottom and a simulation skull top cover. The simulation skull bottom and the simulation skulltop cover are detachably connected to form a simulation skull cavity. A simulated ventricle, a simulated brain tissue, a simulated subarachnoid space, a simulated dura mater and a simulated cerebralhematoma are arranged on the inner side of the simulated skull cavity; and a simulation blood vessel is arranged at the bottom of the inner side of the bottom of the simulation skull. According to theinvention, various structures, including skull, dura mater, subarachnoid space, blood vessels, hematoma, ventricle and the like, of the brain of a cerebral hemorrhage patient can be simulated; so that the simulated surgery of cerebral hemorrhage is close to actual operation in the aspects of image interpretation, operation path design, hematoma positioning, skull drilling, bone window forming, dura mater incision, hematoma puncture, hematoma flushing and drainage, channel implantation, microscope or endoscope hematoma removal and the like as much as possible, various simulated operation operations are performed on the model, and various operation skills of cerebral hemorrhage treatment of clinicians are trained.

Systems and methods for rapid, accurate, fully-automated, brain hemorrhage deep learning (DL) based assessment tools are provided, to assist clinicians in the detection & characterization of hemorrhages or bleeds. Images may be acquired from a subject using an imaging source, and preprocessed to cleanup, reformat, and perform any needed interpolation prior to being analyzed by an artificial intelligence network, such as a convolutional neural network (CNN). The artificial intelligence network identifies and labels regions of interest in the image, such as identifying any hemorrhages or bleeds. An output for a user may also include a confidence value associated with the identification.

The invention belongs to the field of image processing, and particularly relates to a CT image segmentation method based on an improved AU-Net network, and the method comprises the steps: obtaining a to-be-segmented brain CT image, and carrying out the preprocessing of the obtained brain CT image; inputting the processed image into the trained improved AU-Net network for image recognition and segmentation to obtain a segmented CT image; identifying a cerebral hemorrhage area according to the segmented brain CT image. The improved AU-Net network comprises an encoder, a decoder and a hopping connection part. Aiming at the problem of low segmentation precision caused by large size and shape difference of the hemorrhage part of the cerebral hemorrhage CT image, the invention provides a coding-decoding-based structure, and a residual octave convolution module is designed in the structure, so that the model can segment and identify the image more accurately.

The invention relates to an analytical method for beta-amyloid protein pathology by using thioflavine T staining. The method comprises the following processes: A, a patient pathological specimen source, B, an experimental animal pathological specimen source, C, treatment of patient and experimental animal brain tissue specimens, D, immumohistochemical staining of specimen beta-amyloid protein 1-42, E, thioflavine T staining of the specimen, and F, optical / fluorescence microscope pathological examination. The method has the advantages of introducing and widely using the thioflavine T to mark an amyloid protein disease patient brain tissue pathological specimen and assess the pharmacological intervention effect of alzheimer disease (AD) transgenic animals; compared with the traditional silver staining method and A beta immunohistochemical method, the method provided by the invention has the characteristics of being simple and feasible, and sensitive and reliable, is beneficial for clearing the nosetiology of cerebral hemorrhage, and has great guide value on formulation of patient secondary intervening measures. The wide application of the technology has a powerful promoting effect on clinical pathological research and translational medicine research of the A beta related diseases (alzheimer disease and amyloid angiopathy).

The invention discloses a cerebral hemorrhage automatic detection method based on a brain auxiliary image and an electronic medium, and is applied to the technical field of image processing, and the method comprises the steps: carrying out the CT scanning of the head of a patient, and obtaining a brain CT image; generating a brain auxiliary image according to the brain CT image; and inputting thebrain CT image and the brain auxiliary image into a pre-trained neural network, automatically detecting a cerebral hemorrhage area in the brain CT image in combination with the brain auxiliary image,and outputting a mask including the cerebral hemorrhage area and type. According to the invention, the brain auxiliary image and the brain CT image scanned by the patient are combined for use, the cerebral hemorrhage area and type identification accuracy of the neural network is improved, the technical requirements of doctors in the diagnosis process are reduced, and the diagnosis efficiency is greatly improved.

A method for preventing and / or treating ischaemic and / or iron-related retinal or brain disorders comprising administering an effective amount of ferulic acid (FA), tetramethylpyrazine (TMP) or their pharmaceutically acceptable salt, ester, solvate, hydrate, analogs, metabolite, enantiomer, isomer, tautomer, amide, derivative or prodrug to a subject. The former diseases comprise retinal ischemia, glaucoma as well as brain ischaemia (i.e. stroke, infarction typed). The latter ones comprise age-related macular degeneration, intraocular hemorrhage, siderosis oculi (due to retained intraocular iron), oxidative stress of the retina as well as brain hemorrhage (stroke, hemorrhagic type) or Alzheimer disease. Clinically, FA alone or in combination of TMP can be administered systemically, orally, intravitreously, topically (in form of eyedrops), as well as other routes such as periocular, subconjunctival, and intracamera.

According to the 3D printing cerebral hemorrhage model for puncture training and the efficient manufacturing method of the 3D printing cerebral hemorrhage model, the smooth interface of an upper skull and a lower skull is limited and combined through a limiting groove and a limiting boss to form the whole simulation skull, a flexible simulated hematoma block is installed in the lower skull through a skull seat, and the simulation skull is further filled with a flexible simulated brain tissue; the simulated brain tissue wraps the simulated hematoma block, and the simulated brain tissue and the simulated hematoma block are made of transparent materials; after a 3D model is created by imitating any real cerebral hemorrhage case clinically, an individualized model is manufactured through a 3D printing technology and is used for practical puncture operation training; pathophysiological changes of cerebral hemorrhage can be completely simulated, and puncture experience of the model is vivid; after the operation is completed, the path deformation of the puncture needle can be visually inspected through the transparent simulated brain tissue and the simulated hematoma block, and the puncture effect can be clearly judged; and the device is accurate in position, can be repeatedly used or recycled, and is simple in structure, low in cost and convenient to operate.

The invention discloses a cerebral hemorrhage CT image classification method based on image sequence analysis. The method belongs to the technical field of medical image analysis, and the operation process comprises the steps of brain CT image data acquisition, data imaging processing, model construction and classification method implementation. The method comprises the following specific operation steps: acquiring a brain CT scanning result to obtain brain CT image original data; performing imaging processing on the original data of the brain CT image to form a three-channel image sequence as the input of a subsequent model; constructing a model comprising a channel attention module and a space attention module to extract features of the three-channel image sequence; according to the method, the model is trained to optimize parameters, cerebral hemorrhage positive is recognized, cerebral hemorrhage subtypes are distinguished, cerebral hemorrhage CT images are classified, CT scanning image information can be fully utilized by the model, attention to key information in an image sequence is improved, the judgment process of the whole method conforms to the diagnosis process of doctors in a real scene, and the diagnosis efficiency is improved. And the cerebral hemorrhage classification effect can be improved.

The invention relates to soft capsules for treating apoplexy and a preparation method thereof. The inside of each soft capsule shell is extracts of sanguisuge and raidx astragali, also can be added with extracts of auxiliary Chinese medicaments, such as sanchi, snakegourd fruit, earthworm, ginseng and the like, and is added with relevant auxiliary materials, i.e. a dispersing agent, a suspending agent, an antioxygen, a preservative and the like. The preparation method for the soft capsules comprises the following steps: heating, stirring and melting glycerin, distilled water and expanded gelatin in a gelatin pot; adding the preservative in the gelatin pot; adding the extracts of sanguisuge and raidx astragali, the extracts of other auxiliary Chinese medicaments and liquid melt of beeswax and seed fat; and stirring the mixture into the uniform semi-solid substance. The soft capsules whose effective components are highly dispersed in the substrate are prepared by a pressing method or a dropping preparation method. The soft capsules comprising the extract of sanguisuge and raidx astragali are used for activating blood, eliminating stasis, promoting blood circulation and relieving pain, are suitable to treat meridian qi deficiency and blood stasis type cerebral infarction symptoms in the apoplexy, coronary heart disease, angina, acute myocardial infarction and ischemic cerebral apoplexy, can obviously reduce arteria vertebralis resistance and improve cerebral ischemia and brain circulation, and also can be used for disseminated intravascular coagulation and absorption of intracerebral hematoma of cerebral hemorrhage convalescence and sequelae. The soft capsules of the invention have physicochemical property, stable drug effect and high bioavailability, and can cover bad taste and odor of the medicament.

The invention relates to a pharmaceutical composition. The pharmaceutical composition is prepared from phellodendrine, paeoniflorin and optional EGCG (epigallocatechin gallate). The pharmaceutical composition can prevent or treat brain tissue damage caused by local and whole cerebral ischemia, can specifically prevent or treat cerebral hemorrhage, cerebral infarction, cerebral thrombosis and otherdiseases, especially has a very good treatment effect on cerebral infarction, and is high in safety and free from side effect.

The invention relates to novel application of the medical effect of polysaccharide, in particular to application of polysaccharide in a medicament for treating or preventing primary cerebral hemorrhage. An SD (Sprague Dawley) rat cerebral hemorrhage model is used as an experimental material, and the polysaccharide is used for treating an SD rat with primary cerebral hemorrhage neuronal damage, no matter the drug administration is carried out before or after the model, the polysaccharide has the effect of reducing encephaledema (BBB, brain blood barrier) in the cerebral hemorrhage model; drug administration before hemorrhage indicates that the inhibition ratios to brain water content (BBB) are respectively 10.4 percent and 13.3 percent if dosages are 60 and 100mg / kg, and the prevention effect is good; and drug administration before hemorrhage indicates that the inhibition ratios to the brain water content (BBB) are respectively 9.5 percent and 12 percent if dosages are 60 and 100mg / kg. The remarkable medical effect of the polysaccharide in cerebral hemorrhage treatment before clinical application indicates the clinical treatment practicability of polysaccharide in cerebral hemorrhage treatment. The polysaccharide can be used as a prevention medicament and a treatment medicament to improve the cure rate and survival rate of cerebral hemorrhage and has good treatment effect.

The invention discloses a composition for relieving hand and foot numbness caused by cerebral hemorrhage. The composition is mainly prepared from, by weight, 9-15 parts of portulaca oleracea, 6-12 parts of pawpaws, 10-15 parts of Chinese yam, 5-10 parts of aloe, 6-12 parts of radix astragali, 4-8 parts of radix aconiti lateralis preparata, 2-6 parts of tiger bone glue, 4.5-9 parts of gynura segetum, 5-15 parts of ligusticum wallichii, 2-5 parts of radix acanthopanacis senticosl, 5-15 parts of panax ginseng, 2-7 parts of crocus sativus, 3-7 parts of semen cuscutae and 5-10 parts of gastrodia elata. The composition has a remarkable effect of relieving hand and foot numbness caused by cerebral hemorrhage and has the functions of relieving pain, nourishing the brain, calming the nerves, controlling the blood pressure and treating limb numbness, and most of all, the composition can relieve hand and foot numbness caused by cerebral hemorrhage.

The invention relates to an artificial intelligence technology, and discloses an intelligent cerebral hemorrhage point detection method. The method comprises the steps of obtaining a brain medical image set and obtaining a readable brain image set based on a parameter adjustment algorithm, dividing the readable brain image set into a training set and a test set, inputting the training set into anoriginal cerebral hemorrhage point detection model for training to obtain a cerebral hemorrhage point detection model, inputting the test set into the cerebral hemorrhage point detection model to obtain a test value, and after the test value meets the preset requirement, enabling the brain bleeding point detection model to complete the training, receive a brain picture, input the brain picture into the brain bleeding point detection model to obtain a brain bleeding point coordinate, and editing, arranging and outputting a brain bleeding point based on a bleeding point operation platform and the brain bleeding point coordinate. The invention further provides a cerebral hemorrhage point intelligent detection device and a computer readable storage medium. The cerebral hemorrhage point detection method and device can realize an accurate and efficient cerebral hemorrhage point detection function.

The invention discloses a cerebral hemorrhage CT (Computed Tomography) radiography scanning system, relates to the technical field of cerebral CT image analysis, and aims to solve the problem of high labor cost in traditional CT image processing, a watershed algorithm and a seed growth method are organically fused, an operator only needs to import a craniocerebral CT image into the system and select the craniocerebral CT image according to requirements, a hemorrhage area can be segmented, and the operation is simple and convenient. The bleeding area is accurately quantified, labor cost is reduced, and time is saved. And meanwhile, bleeding parts in the brain CT image are segmented and stored in batches, so that doctors in different hospitals can read the bleeding parts subsequently, storage and electronic visualization are facilitated, and the system can scan the CT to obtain corresponding electronic files so as to perform subsequent CT image processing.

The invention discloses a modeling method of a mouse hypertensive cerebral hemorrhage model, which comprises the following steps of: puncturing and taking blood from the left ventricle of a mouse, exposing a skull surgery field by wiping and cleaning soft tissues covering the skull, drilling after determining a needle insertion point on the surface of the skull, injecting autologous blood at the drilling position through a brain stereotaxic instrument, and then injecting the autologous blood into the mouse hypertensive cerebral hemorrhage model; and after injection is completed, sealing the drilled hole with bone wax, disinfecting the incision, and suturing the skin. According to the method, arterial blood is taken through left ventricle puncture, the survival rate of a mouse is not reduced on the premise that sufficient arterial blood is extracted, autologous arterial blood is accurately injected back into the tail shell core of the basal segment in the brain through a mouse brain locator, and stable hematoma is formed. The method provides guarantee for subsequent experiments, is beneficial to experimental contrast research, is very similar to clinical pathological changes and disease outcome of hypertension patients, and has important significance on disease outcome and treatment schemes after cerebral hemorrhage.

The invention discloses an application of apolipoprotein E receptor mimetic peptide 6KApoEp in preparation of a medicine for treating secondary brain injury after cerebral hemorrhage, and discloses a protein sequence of the apolipoprotein E receptor mimetic peptide 6KApoEp, a construction method of the protein sequence of the apolipoprotein E receptor mimetic peptide 6KApoEp and preparation of an application mixed solution; after the 6KApoEp is applied, the expression of CypA can be reduced; by inhibiting activation of a / MMP-9 pathway, cerebral edema and blood-brain barrier damage after cerebral hemorrhage and generation of proinflammatory factors are relieved; the brain water content is reduced, the BBB permeability is improved, the increase of blood-brain barrier related proteins such as claudin-5, occludin and ZO-1 is promoted, the inflammatory response after cerebral hemorrhage is regulated and controlled by inhibiting CypA / NF-KB / MMP-9, the water content of brain tissues is reduced, and the blood-brain barrier permeability is improved, so that the secondary brain injury after cerebral hemorrhage is relieved, and the neuroprotective effect on cerebral hemorrhage is achieved; the inflammatory response after cerebral hemorrhage is reduced, and the blood-brain barrier permeability is improved.

The invention belongs to the field of image processing, and particularly relates to a CT image three-dimensional reconstruction method based on an MC-T algorithm, and the method comprises the steps: obtaining a to-be-reconstructed cerebral hemorrhage CT image and a cerebral hemorrhage CT focus mask image; preprocessing the obtained cerebral hemorrhage CT image and the cerebral hemorrhage CT focus mask image; reconstructing the preprocessed image data by adopting an MC-T algorithm to obtain a reconstructed three-dimensional image; aiming at the problems of low calculation speed and ambiguity in the traditional MC algorithm, the invention provides an improved three-dimensional reconstruction algorithm based on the MC algorithm, the algorithm takes a two-dimensional cerebral hemorrhage CT image and a focus segmentation mask slice as input, and detection of empty voxels is effectively eliminated through a voxel edge marking method in a three-dimensional data field.

The invention discloses a 3D operation guide plate for a cerebral hemorrhage operation. The 3D operation guide plate comprises a base, a puncture part supported by the base and a fixing part connectedwith the base and fixed to the surface of a human body. The fixing part comprises a fixing band tightly attached to the brain in a winding mode and a fixing patch attached to the fixing band, and concave positioning points which are embedded with the fixing patch to fix the base are arranged on the lower surface of the base; and the puncture part comprises a connecting section connected with thebase and a puncture guide section used for puncture positioning, wherein the connecting section is hollow in inner part, and a guide channel is formed in the puncture guide section. Compared with theprior art, the 3D operation guide plate for cerebral hemorrhage operation is obvious in artificial bony landmark, firm and free of displacement, the range of the operation guide plate can be freely designed, the operation process is simplified, and the operation accuracy is improved.

The invention discloses functional formula food and application thereof in preparation of a medicine for preventing and treating secondary brain injury after cerebral hemorrhage, and belongs to the technical field of medicines. The functional formula food is prepared from the following raw materials: docosahexaenoic acid, eicosapentaenoic acid, L-serine, taurine, whey protein, vitamin C, vitamin E and beta-carotene. The functional formula food disclosed by the invention can be used for remarkably reducing the cerebral hemorrhage volume and obviously improving the neurological function, is used for preventing and / or treating secondary brain injury after cerebral hemorrhage, and provides a new thought for medicine research on cerebral hemorrhage.

The invention discloses a multi-frequency electromagnetic tomographic method for detection of cerebral hemorrhage. Multiple coils are distributed on the periphery of a detected area, exciting coils are sequentially powered up with alternating excitation currents at different frequencies, detection coils around a detected area produce induced voltages sequentially at different frequencies, and the target cerebral hemorrhage image is reconstructed in steps as follows: the detection voltage difference produced by a brain suffering from cerebral hemorrhage on the detection coils is calculated; phase shift, caused by the brain suffering from cerebral hemorrhage when the frequency of excitation currents is fi, of detection voltage on the detection is calculated; the formula is solved with a Tikhonov regularization method, the phase shift, caused by single tissue j when the reference frequency of the excitation currents is f1, of the detection voltage on the detection coils is acquired; the phase difference, caused by cerebral hemorrhage tissue when the frequency of the excitation currents is between fn and f1, of the detection voltage on the detection coils is calculated; the electric conductivity distribution of the cerebral hemorrhage tissue is solved.

A pyrazolone derivative represented by formula (I) below:wherein R1 to R3 are the same as defined in claims; or an optical isomer, a pharmaceutically acceptable salt thereof, or a hydrate or solvate thereof is provided. The novel pyrazolone derivative according to the present invention has a PAI-1 production inhibitory activity, a tissue fibrosis inhibitory activity, and a fibrolytic activity, and is effective for preventing and / or treating tissue fibrotic diseases (lung fibrosis, kidney fibrosis, etc.) and diseases of which a pathological thrombus becomes the cause, such as ischemic cardiac diseases (cardiac infarction and angina pectoris), atrial thrombus, lung embolism, deep thrombophlebitis, disseminated intravascular clotting, ischemic brain diseases (brain infarction, brain hemorrhage), and arterial sclerosis. In addition, a pharmaceutical agent for preventing and / or treating the disease conditions or the symptoms mediated by plasminogen activator inhibitor-1, comprising the novel pyrazolone derivative according to the present invention is also provided.

The invention belongs to the technical field of medicines, and relates to application of a beta 3-adrenergic receptor agonist in preparation of a medicine for treating or preventing brain injury. Theresearch finds that the beta 3-adrenergic receptor agonist can increase Ly6Clow mononuclear cells and macrophages expressing alternative activation markers (CD206 and PD-L2) in the brain of a cerebralhemorrhage model mouse, and reduce neutrophil and lymphocyte which are infiltrated by brain tissues; and the beta 3-adrenergic receptor agonist promotes intramedullary hematopoiesis of the Ly6Clow mononuclear cells, promotes the Ly6Clow mononuclear cells and the macrophages to express IL-10, can effectively inhibit focal brain inflammation and edema after cerebral hemorrhage, and has important clinical application value for treating the brain injury after the cerebral hemorrhage. The invention further discloses a pharmaceutical composition. The pharmaceutical composition comprises the beta 3-adrenergic receptor agonist, and can be used as a medicine for treating the brain injury caused by the cerebral hemorrhage.

The invention relates to a traditional Chinese medicine composition for treating cerebral hemorrhage, which belongs to the technical field of medicine and consists of dried bitter gourd, loofah, Alisma, Polygonum cuspidatum, Astragalus, Imperatae, Ginkgo biloba, Zhuru, Cassia chinensis, Tianzhu Huang, Tribulus terrestris, Licorice and other traditional Chinese medicine raw materials are prepared, and all prescriptions can be used in conjunction with each other to invigorate qi and essence, replenish qi and activate blood, refresh the brain, calm liver yang, clear heat and eliminate phlegm, clear liver and wind, reduce intracranial pressure, and shrink the brain. The effect of internal hematoma, so as to achieve the effect of effective treatment of cerebral hemorrhage.

The invention relates to a method and device for cerebral hemorrhage lesion identification and hematoma enlargement prediction. The method comprises the steps: segmenting target images to obtain a regional mask of a lesion, wherein the target images comprise brain CT images; according to the target images and the regional mask of the lesion, extracting radiomics characteristics of the lesion; and obtaining a prediction result of the focus enlargement possibility in the target images according to the radiomics characteristics. According to the embodiment of the invention, the target images are segmented to obtain the regional mask of the lesion, the radiomics characteristics of the lesion are extracted according to the targets image and the regional mask of the lesion, and the prediction result of the lesion enlargement possibility in the target image is obtained according to the radiomics characteristics, such that the lesion can be quickly and accurately identified, and the lesion enlargement possibility is identified. The method and device for cerebral hemorrhage lesion identification and hematoma enlargement prediction have the characteristic of automation, and are free of manual assistance and manual operation.

The invention discloses an improved Unet-based automatic detection system for cerebral hemorrhage in CT images, which includes an image preprocessing module for obtaining brain CT images, and performing cutting and scaling processing on brain CT images after extracting brain parenchyma; The hemorrhage area detection module uses the improved Unet network to mark the position of the cerebral hemorrhage area on the brain CT image extracted from the brain parenchyma; the improved Unet network includes the RCSP convolution module, the CBL4 convolution module, the feature pyramid attention mechanism module, and the multi-scale A feature skip connection module and an output module; a data analysis module for estimating the total volume of hemorrhage and generating a three-dimensional image of the brain hemorrhage area. The invention realizes the automatic detection of cerebral hemorrhage, the estimation of the total volume of the hemorrhage area and three-dimensional imaging, effectively reduces the subjective error of manual segmentation and the workload of doctors, provides effective data support for clinical decision-making, and realizes Unet to detect cerebral hemorrhage , using more contextual semantic information in CT images, the detection accuracy is higher.

The invention relates to the technical field of animal model construction, in particular to a method for constructing a canine cerebral hemorrhage model. The method comprises the following steps of sequentially cutting skin and subcutaneous tissues, separating cranial top muscles and exposing skull by taking a sagittal seam at the rear top of the head of a model dog after prone position fixation and anesthesia as an incision, moving 1.5-2.5 cm from the joint of the crest and the sagittal crest to the face direction, and then moving 0.5-1.5 cm to the right outer side to open a bone window, opening the dura mater, exposing the top lobe of the brain tissue, and clamping the cerebral cortex tissue after hemostasis, wherein the clamping range is not more than 3mm *3mm, and the clamping depth is not more than 2mm. The hemorrhage model can reflect the tiny errhysis condition in the neurosurgery operation process, the construction method is easy to operate, no adverse reaction exists, and the success rate is high.

The invention discloses a cerebral hemorrhage prediction method and system based on a PCA-BP neural network, and the method comprises the following steps: collecting human physiological data and arm amplitude data through a physiological information collection module and an arm amplitude detection module respectively, and taking the data as the input of a cerebral hemorrhage probability prediction model and an arm amplitude detection model; establishing a cerebral hemorrhage probability prediction model and an arm amplitude detection model through a PCA-BP neural network algorithm; whether the detected human body suffers from cerebral hemorrhage or not is judged through the cerebral hemorrhage probability prediction model, and whether the detected human body is paralyzed or not is judged through the arm amplitude detection model. The cerebral hemorrhage probability prediction model and the arm amplitude detection model are established through the PCA-BP neural network algorithm, cerebral hemorrhage is predicted in combination with the cerebral hemorrhage probability prediction model and the arm amplitude detection model, and accurate judgment of human cerebral hemorrhage is improved to a great extent.