81 results about "Brain hemorrhages" patented technology

The invention discloses a cerebral hemorrhage image recognition method, and aims to solve the problems that different cerebral hemorrhage focuses have significant differences in form, size and position, and cerebral anatomical structures of different individuals also have significant differences, so that the features of cerebral hemorrhage images are complex and changeable, and the recognition accuracy is high. Therefore, a traditional image processing method is difficult to accurately identify the key information of the focus in the cerebral hemorrhage image. The method comprises the steps of obtaining a cerebral hemorrhage image; the cerebral hemorrhage image is input into the trained cerebral hemorrhage image recognition model to obtain a recognition result output by the model, and the recognition result comprises the lesion type, position and size of the lesion in the cerebral hemorrhage image; wherein the cerebral hemorrhage image recognition model is obtained by training an enhanced cerebral hemorrhage image sample obtained by performing elastic deformation processing on a cerebral hemorrhage image sample. The invention further discloses a cerebral hemorrhage image recognition device, electronic equipment, a computer readable storage medium and a computer program product.

The invention relates to the technical field of internet big data, in particular to a cerebral hemorrhage space positioning and prognosis prediction network system based on three-dimensional point cloud. The cerebral hemorrhage space positioning system comprises an image acquisition module used for acquiring a brain CT image to be processed; the offset correction module is used for performing offset correction on the brain CT image to obtain a corrected brain CT image; the hematoma region segmentation model is used for segmenting the corrected brain CT image to obtain a hematoma region; the point cloud calculation module is used for calculating three-dimensional space coordinates of hematoma voxels in a hematoma area in a brain coordinate system based on the corrected brain CT image and taking the three-dimensional space coordinates as point cloud data of the hematoma area; and the point cloud data output module is used for performing normalization processing on the point cloud data of the hematoma area to obtain hematoma three-dimensional point cloud data representing the hematoma three-dimensional space position. According to the method, an accurate and comprehensive data basis is provided for cerebral hemorrhage prognosis prediction, and the accuracy and comprehensiveness of subsequent cerebral hemorrhage prognosis prediction are improved.

The invention relates to the technical field of medical instruments, in particular to a cerebral hemorrhage drainage device with a breaking and sucking function, which comprises a base, a support frame is fixedly mounted at the upper end of the base, a breaking mechanism is arranged on the back of the support frame, and a drainage assembly is arranged in the support frame. Through the arrangement of the crushing mechanism, blood clots and fragments can be effectively crushed and sucked out through the absorption assembly while drainage is conducted, so that it is guaranteed that hematoma is completely removed, the hematoma recurrence risk is reduced, and the drainage effect is improved; by means of the breaking and sucking function, blood clots and fragments are prevented from blocking the drainage tube, it is guaranteed that blood can flow out smoothly, and complications are reduced; by efficiently removing hematoma, compression and injury of brain tissue are reduced, nerve recovery is promoted, and the hospitalization time and rehabilitation cycle of a patient are shortened; blood clots and fragments are effectively removed, the condition of incomplete drainage or blockage is reduced, and the incidence rate of complications such as infection and hematoma recurrence is reduced.

The invention discloses a cerebral hemorrhage volume measurement method and related equipment. The method comprises the following steps: acquiring brain medical image data to be measured; inputting the brain medical image data into a three-dimensional segmentation network for cerebral hemorrhage region segmentation to obtain a cerebral hemorrhage region image; identifying a cerebral hemorrhage stage of the cerebral hemorrhage area image according to the cerebral hemorrhage area image; constructing a standard hemorrhage template based on the cerebral hemorrhage stage and the lesion anatomical position in the cerebral hemorrhage area image; performing gradient response analysis based on the feature map of the last convolutional layer in the three-dimensional segmentation network to generate an interpretation map; performing spatial similarity analysis based on the standard bleeding template and the interpretation graph to obtain a consistency score between the standard bleeding template and the interpretation graph; according to the cerebral hemorrhage area image, calculating an initial cerebral hemorrhage volume through a preset dual-path estimation model; and adjusting the fusion weight of the dual-path model according to the consistency score, and determining the target cerebral hemorrhage volume according to the adjusted fusion weight and the initial cerebral hemorrhage volume.

The invention provides a cerebral hemorrhage CT image segmentation method and system based on an adapter and high-resolution feature extraction. The method comprises the following steps: constructing a cerebral hemorrhage CT image segmentation network which comprises an improved SAM encoder, a high-resolution feature extraction module, a fusion module and a mask decoder; the improved SAM encoder is obtained by introducing an adapter module into the SAM encoder; extracting low-resolution features from the input image by using an improved SAM encoder; extracting high-resolution features from the input image by using a high-resolution feature extraction module; the fusion module is used for fusing the two resolution characteristics; the mask decoder is used for generating a segmentation mask based on the fused features; training the cerebral hemorrhage CT image segmentation network by using a low-resolution cerebral hemorrhage CT image pair and a high-resolution cerebral hemorrhage CT image pair to obtain a segmentation model; and performing down-sampling on a to-be-segmented high-resolution image to obtain a corresponding low-resolution image, and jointly inputting the two images into the segmentation model to obtain a segmentation result.

The invention relates to the technical field, in particular to a cerebral hemorrhage intelligent decision support system based on deep adaptive feature fusion, which comprises a multi-modal data standardization module, a cross-modal feature fusion module, a focus segmentation calculation module, a hemorrhage type identification module and an illness state grading output module. According to the method, deep association between fusion features and bleeding types is mined through an attention mechanism, related feature indexes are converted into standardized scores by referring to clinical common scoring standards, model attention weight distribution is optimized by combining actual prognosis result deviation, the suitability of illness state grading and the clinical scoring standards is improved, and the probability of illness state grading is lowered. An accurate grading result and prognosis prediction reference are provided for clinical treatment decision and rehabilitation intervention; effective data are screened from multiple types of brain images according to image quality related indexes, clinical text key information extraction and association labeling are combined, data integrity and consistency verification is carried out at the same time, and the standardization degree of multi-source data is improved.

Embodiments of the present application provide a brain hemorrhage surgery robot and an electronic device. The brain hemorrhage surgery robot comprises a control host and a mechanical arm, and a preprocessing module, an intracranial hematoma prediction model and a post-processing module are arranged on the control host. The preprocessing module is used for preprocessing a to-be-processed brain axial tomography grayscale image to convert it into an input image of the intracranial hematoma segmentation module. The intracranial hematoma prediction model is used for feature extraction and voxel classification on the input image to obtain a prediction result of intracranial hematoma. The post-processing module is used for three-dimensional reconstruction of intracranial hematoma according to the prediction result of intracranial hematoma to obtain an intracranial hematoma model to control the action of the mechanical arm.

The invention belongs to the technical field of biological medicines, and particularly relates to application of Chi3l1 as a target spot in preparation of a medicine for preventing or treating secondary brain injury after cerebral hemorrhage. By integrating space transcriptomics and a mononuclear RNA sequencing technology, the spatial heterogeneity and cell type specificity of gene expression in ICH afterbrain tissue are deeply analyzed, a group of astrocyte subgroups AST1 with neuritis existing around hematoma in the acute stage after cerebral hemorrhage is identified, Chi3l1 is determined as a key inflammatory effect factor of the AST1 subgroups, and the AST1 subgroups with neuritis are used as the key inflammatory effect factor of the AST1 subgroups. And the influence of the gene on the phenotypic transformation of astrocytes and microglial cells is verified. The discovery provides an important theoretical basis for developing a treatment strategy of targeting Chi3l1, and is expected to improve neuroinflammatory response and neurological dysfunction after ICH by regulating and controlling expression of the AST1 subgroup and Chi3l1, and opens up a new direction for treatment of ICH.

The invention discloses a cerebral hemorrhage magnetic induction tomography tensor compressed sensing acquisition method and system, which is applied to the technical field of magnetic induction tomography, and comprises the following steps: arranging a coil around the human brain, acquiring an induction electric signal generated on the coil, and converting the induction electric signal into a three-dimensional signal; carrying out sparse processing on the three-dimensional signal, constructing and obtaining a three-dimensional tensor under recovered sparse representation by a sparse representation method, and carrying out sparse sampling on the three-dimensional tensor to obtain measurement data; and based on measurement data, performing reconstruction processing on the three-dimensional tensor under the recovery sparse representation by adopting an inverse discrete cosine transform method, and performing construction to obtain a reconstructed three-dimensional tensor signal. In this way, the signals on the sensor array are expressed as the tensor, the tensor compressed sensing operation is carried out, the data collection amount can be effectively reduced, the data collection time is shortened, and an effective method is provided for miniaturization and real-time performance of a cerebral hemorrhage MIT system.

This invention discloses a training method, system, and device for intracranial hemorrhage recognition model training and intracranial hemorrhage recognition. The method includes: S1, constructing an intracranial hemorrhage recognition model, which includes a first-stage network for region segmentation and a second-stage network for hemorrhage recognition; S2, training the first-stage network; and S3, training the second-stage network to complete the training of the intracranial hemorrhage recognition model. The intracranial hemorrhage recognition method includes: acquiring CT images scanned from a patient, inputting the CT images into the intracranial hemorrhage recognition model, and outputting the predicted hemorrhage area and hemorrhage type. This invention proposes a two-stage intracranial hemorrhage analysis model, which can simultaneously perform region segmentation and site identification of intracranial hemorrhage, helping to provide more specific and effective auxiliary diagnostic opinions in practical applications.

The application discloses a brain hemorrhage prognosis improvement method based on intestinal flora regulation and relates to the technical field of intestinal microecology.The application comprises the following steps: detecting feces, starting intervention if the enterococcus abundance and neuroinflammatory metabolic markers exceed the standard, stopping the use of conventional nutrient solution, perfusing a special component containing sugar analogs, blocking the energy uptake of enterococcus, simultaneously providing a carbon source for beneficial bacteria, synchronously perfusing a microsphere suspension containing a molecular capture function, adsorbing and fixing proinflammatory metabolic waste in the intestinal tract, blocking the blood entry of the proinflammatory metabolic waste, perfusing live bacteria with different functions three times in time sequence, sequentially completing the acidification of the environment, constructing a bacterial membrane barrier and repairing the intestinal epithelium, and re-detecting after each round of intervention, selecting the maintenance period or adjusting the intensity and then recycling according to the decrease of enterococcus and markers.The application can limit the competitive advantage of enterococcus in the utilization of carbon sources after brain hemorrhage by sequentially implementing competitive inhibition of the phosphotransferase system and multi-species ecological niche occupation.

The application relates to a cerebral hemorrhage medical image fusion method and system. The method utilizes the feature that the brain structure has a certain symmetry, equally divides the brain structures in a target brain image and a reference brain image into two subimages, and when a first feature point and a second feature point are matched, a third feature point and a fourth feature point in another subimage can be used to assist the first feature point and the second feature point in matching. Moreover, the matching process of any pair of feature points is that a plurality of neighbor feature points of one feature point are mapped into the space of another feature point, then the mapping difference values are calculated, and then under the condition that the two difference values are less than a set value, it is judged that the first feature point and the second feature point are matched successfully. The method can improve the matching accuracy of the feature points and finally improve the image fusion effect.

The invention discloses a cerebral hemorrhage minimally invasive drainage auxiliary device for the neurosurgery department, and relates to the technical field of cerebral hemorrhage minimally invasive drainage. A position adjusting assembly is arranged at the top of the bottom plate, a guide plate is connected to the position adjusting assembly, a mounting groove and a guide groove are formed in the top of the guide plate, and the rear end of the mounting groove is communicated with the front end of the guide groove. The position and the angle of the guide plate can be flexibly adjusted through the arranged position adjusting assembly, so that the front end of the guide plate is aligned with the pre-designed insertion direction of the drainage tube, and then the drainage tube can be conveyed and inserted into the designated position of the brain of a patient in the set insertion direction through the tube conveying assembly. In this way, it can be guaranteed that the drainage tube is not prone to deviation in the conveying and inserting process, it is guaranteed that the drainage tube can be accurately inserted into a designated position, the effect and safety of minimally invasive drainage treatment are improved, and therefore the reliability and practicability of the auxiliary device are improved.

The application provides a traditional Chinese medicine preparation for treating or improving cerebral hemorrhage and a preparation method thereof, and relates to the technical field of traditional Chinese medicine pharmacy. The traditional Chinese medicine preparation is composed of nacre, antelope horn powder, dragon's blood, Herba Schizonepetae, Prunella vulgaris, Stink-bug, Smilax riparia, bamboo juice, dried tangerine or orange peel, clubmoss, radix puerariae, Zizania aquatica and leaf of Chinese pear. The preparation has a significant therapeutic effect on cerebral hemorrhage, can obviously improve the neurological deficit of cerebral hemorrhage rats, reduce the water content of brain tissue to alleviate brain edema, simultaneously alleviate the inflammatory response in the body, thereby playing a neuroprotective effect on cerebral hemorrhage rats. In addition, the preparation can obviously improve the consciousness state of cerebral hemorrhage patients, alleviate the degree of neurological deficit, relieve the related TCM syndromes of the patients, simultaneously effectively improve the daily life ability of the patients, significantly improve the total effective rate of clinical treatment, and no obvious adverse reactions are observed in the treatment process, and the safety is good, thereby providing a safe and effective treatment scheme for the conservative treatment of cerebral hemorrhage.

The invention provides a traditional Chinese medicine preparation for treating or improving cerebral hemorrhage and a preparation method thereof, and relates to the technical field of traditional Chinese medicine pharmacy, the traditional Chinese medicine preparation is composed of nacre mother of pearl, antelope horn powder, dragon's blood, motherwort fruit, selfheal, aspongopus, radix actinidiae chinensis, bamboo juice, pericarpium citri reticulatae, selaginella tamariscina, radix puerariae, zizania aquatica and folium eriobotryae. The traditional Chinese medicine composition can obviously improve neurological impairment of cerebral hemorrhage rats, reduce the water content of brain tissues to relieve encephaledema and reduce inflammatory response in vivo, thereby playing a role in protecting the nerves of the cerebral hemorrhage rats. Besides, the preparation can obviously improve the consciousness state of a cerebral hemorrhage patient, relieve the degree of neurological impairment, relieve related traditional Chinese medicine syndromes of the patient, effectively improve the daily living ability of the patient and obviously improve the total effective rate of clinical treatment, no obvious adverse reaction is observed in the treatment process, and the preparation is good in safety and free of toxic and side effects. And a safe and effective treatment scheme is provided for the conservative treatment of cerebral hemorrhage.

The application particularly relates to a brain hemorrhage pseudo-health image generation method based on pathological decoupling, which comprises the following steps: constructing and training a pseudo-image generation model; in each training iteration: firstly, inputting a pathological image serving as training data into a segmenter, segmenting a pathological region mask from the pathological image through the segmenter; then, inputting the pathological region mask and the pathological image into a generator, generating a pseudo-health image through the generator; subsequently, inputting the pseudo-health image and the pathological region mask into a reconstructor, generating a reconstructed pathological image through the reconstructor; finally, training the pseudo-image generation model based on a total loss of the segmenter, the generator and the reconstructor; and generating a corresponding pseudo-health image through the generator of the trained pseudo-image generation model. The application can ensure that the original identity of a pathological image remains unchanged when removing a pathological region, and can realize one-to-one mapping of the pathological region in the process of generating a reconstructed pathological image.

The utility model relates to a non-contact type multifunctional neurosurgery brain cotton and gelatin sponge transfer tray which comprises an upper tray and a lower tray which can be combined, a hollow cylinder is arranged at one corner of the upper tray, a pin hole column matched with the hollow cylinder through a pin shaft is arranged at one corner of the lower tray, a plurality of partition plates are arranged in the upper tray, and the partition plates are arranged in the lower tray. The upper tray is divided into a plurality of brain cotton storage areas through the partition plates, and a downward-concave circular groove used for storing an aneurysm temporary clip is formed in the lower tray. The utility model designs a double-layer opening and closing type handheld tray which can be opened in a fan-shaped manner when in use. Four kinds of brain cotton of different sizes and models can be placed on the first layer, and meanwhile brain cotton threads can be stretched and cannot be wound mutually; gelatin sponges with different sizes and models can be placed on the second layer, and an aneurysm temporary clip can be placed on the circular sunken part. When a doctor uses the device, a nurse can deliver the brain cotton and the gelatin sponge at the same time, delivery time is saved, and the device is of great significance in dealing with cerebral hemorrhage in an emergency.

The invention belongs to the technical field of biological medicine, and particularly relates to a nano-micelle preparation loaded with minocycline and application of the nano-micelle preparation to treatment of cerebral hemorrhage, the nano-micelle preparation is prepared by taking a polyethylene glycol-polycaprolactone nano material PEG3000-PCL2000 as a carrier, and jointly loading minocycline MINO and a CD147 monoclonal antibody Anti-CD147, so that the nano-micelle preparation is prepared. And the bionic nano-drug MINO (at) PNM (at) CD147 with an active targeting function is constructed. The nano-micelle preparation has a brain targeting property and can be enriched in cerebral hemorrhage tissues, so that the local drug concentration and the treatment efficiency are remarkably improved; the traditional Chinese medicine composition can improve neurological impairment caused by cerebral hemorrhage and significantly reduce the volume of cerebral hematoma, and has an obvious treatment effect on cerebral hemorrhage; the number of inflammatory cells in the peripheral area of hematoma and expression of inflammatory mediators can be remarkably reduced, and therefore the inflammatory response in cerebral hemorrhage tissue is relieved.

The invention discloses a cerebral hemorrhage scalp acupuncture treatment effect prediction method and system based on machine learning, and relates to the field of medical artificial intelligence, clinical baseline data, electrophysiological data, brain function image data, motor function quantitative data and scalp acupuncture treatment parameters of a cerebral hemorrhage patient are collected, and after standardization processing, a standardized data set is obtained; image features, electrophysiological features, clinical function features and treatment parameter features are extracted from the standardized data set, a heterogeneous graph containing patient nodes, feature nodes and treatment parameter nodes is constructed, and correlation edges, correlation edges and time sequence edges among the nodes are defined; according to the invention, through multi-modal data fusion and heterogeneous map construction, in combination with a time sequence attention mechanism, complex association between clinical, electrophysiology, images, motion functions and scalp acupuncture treatment parameters is comprehensively captured, and the accuracy and reliability of curative effect prediction are significantly improved.

The present invention discloses a method for extracting blood clots from cerebral hemorrhage CT images based on optimized SFLA and clustering. Aiming at the aggregation characteristics, complex spatial positions and shapes in cerebral hemorrhage CT images, first, a cerebral hemorrhage clustering algorithm and an improved shuffled frog leaping algorithm (MSFLA) are proposed to segment cerebral hemorrhage CT images, effectively improving the convergence speed and global optimization ability, and obtaining a binary segmentation result of cerebral hemorrhage; then a framework for extracting intracranial blood clots (using a two-dimensional prefix sum elimination algorithm based on an adaptive window) is established to remove irrelevant brain tissues, and finally, by judging the spatial positions of the blood clots and the skull, and using regional morphological operations, efficient and accurate extraction of blood clots is achieved, the extraction contour is more detailed, and the diagnostic error is reduced.

The application provides a neurosurgical brain puncture operation robot and electronic equipment, in the neurosurgical brain puncture operation robot, a control host is used for matching a brain CT image to be planned with an intracranial hematoma puncture path database constructed to determine a hematoma puncture planning path, and the mechanical arm is controlled according to the hematoma puncture planning path to drive the surgical instrument to reach the hematoma position of the brain.In the embodiment of the application, only the CT image scanned in the diagnosis process is used as the brain CT image to be planned, and no other additional image is needed, and the intracranial hematoma puncture path database constructed is matched, so that the planning of the intracranial hematoma puncture path is completed only using the brain tissue in a short time, the planning efficiency is improved, and moreover, the planning process does not need additional manual operation, and the implementation difficulty is smaller for young doctors and primary doctors with less clinical experience, and on this basis, the treatment efficiency of the patient with cerebral hemorrhage is effectively improved.

The present specification relates to the technical field of medical robots, and specifically discloses a cerebral hemorrhage surgery planning system and method, wherein the system comprises: an image storage device configured to store preoperative brain image data of a target object; an image processing device configured to read the preoperative brain image data of the target object from the image storage device; further configured to identify a cerebral hemorrhage type of the target object based on the preoperative brain image data; and further configured to determine a target cerebral hemorrhage surgery mode of the target object according to the preoperative brain image data and the cerebral hemorrhage type. The above scheme can realize automatic hematoma type identification and personalized surgery planning, and improve the efficiency and reliability of surgery planning.

The application discloses application of a MAC-1 agonist in preparation of a medicine for treating and / or relieving cerebral hemorrhage. Specifically disclosed is the use of Leukadherin-1 (LA-1) or a pharmaceutically acceptable salt, isomer or derivative thereof in preparation of a medicine for treating cerebral hemorrhage and secondary brain injury thereof. The medicine can inhibit the migration of immune cells across the blood-brain barrier, reduce cerebral edema, promote hematoma absorption and reduce neural inflammation by regulating the MAC-1-mediated immune adhesion signal pathway, thereby exerting a neuroprotective effect. Meanwhile, a pharmaceutical composition containing the MAC-1 agonist is provided. The application provides a new target and a drug development strategy for cerebral hemorrhage treatment.

The invention relates to a microwave-induced thermoacoustic transcranial quantitative imaging method based on a REAGU-Net network, and the method achieves the simultaneous quantitative reconstruction of dielectric constant, conductivity and sound velocity in brain tissue through the MITAT technology, and provides a new methodology for the characteristic analysis of the brain tissue. A REAGU-Net novel network is developed, an attention guiding block and a residual error inducing block are combined to process the influence of acoustic non-uniformity on reconstruction quality, and effective application of deep learning in quantitative reconstruction is shown; the technology not only shows a good result in cerebral hemorrhage detection, but also can be potentially applied to detection and diagnosis of various diseases including breast cancer, liver diseases and thyroid diseases, and a new quantitative analysis tool is provided for clinic; the DL-MITAT method provided by the invention can provide quantized physical characteristic data, and the data not only is helpful for imaging, but also can provide support for physiological information prediction and the like in subsequent electromagnetic treatment; compared with a traditional TCD or ultrasonic imaging method, the transcranial MITAT has the remarkable advantages that due to the fact that ultrasonic waves of the transcranial MITAT only need to be transmitted with the skull for one time, the possibility of image attenuation and degeneration is reduced, and the imaging quality is improved.

A blood-based diagnostic system for intercranial hemorrhage (ICH) detection includes a sample processing module for processing a blood sample collected from a patient suspected of suffering from ICH, an amino acid detection module for detecting presence of a first amino acid and a second amino acid in the blood sample so processed, an analysis module for calculating a ratio of the first amino acid so detected to the second amino acid so detected to produce a calculation result, and a user interface for communicating the calculation result to a user. In embodiments, the blood-based diagnostic system is implemented as a lateral flow assay. An associated method of operating a blood-based diagnostic system for ICH detection is also disclosed.

The application discloses a brain hemorrhage magnetic induction tomography image reconstruction method based on an improved NR algorithm, and comprises the following steps: obtaining coil detection phase data and a sensitivity matrix by using an established brain hemorrhage MIT finite element model; introducing a regularization penalty term based on a target function of a traditional NR algorithm and solving an iterative formula of the algorithm, determining optimization parameters in the algorithm by a v method, and taking a conductivity distribution calculated by using a linear back projection algorithm as an initial value of iteration of the improved NR algorithm; introducing a projection operator P Ensuring that the algorithm converges on a convex set each time; determining an optimal threshold value or a maximum number of iterations, and outputting a final conductivity distribution. Compared with a traditional magnetic induction tomography image reconstruction algorithm, the application has better image reconstruction quality, can effectively reduce image reconstruction artifacts, and can detect brain hemorrhage.

The disclosure provides a kind of cerebral hemorrhage analysis method and system based on image registration, comprising: automatically segmenting cerebral hemorrhage area in brain CT image;The cerebral CT image and the segmented cerebral hemorrhage image are pretreated;Cerebral CT image is registered according to MRI template, and the deformation field is obtained;The cerebral hemorrhage image is transformed using the deformation field;Analysis patient bleeding level and the brain area involved.Use normal brain MRI image as registration template, register patient brain CT with MRI template, extract patient hematoma feature, can quickly and effectively analyze bleeding level and the brain area involved by hematoma, provide guidance for doctors, and can be used for subsequent visualization modeling, help doctors to formulate more comprehensive treatment plan.

The invention provides an application of edible rubber seed oil in preparation of a medicine or nutritious food for preventing and / or treating hemorrhagic diseases. The edible rubber seed oil can be used for preventing and / or treating liver hemorrhage, cardiac hemorrhage and cerebral hemorrhage. The invention can provide a new safer nutritional food choice for bleeding of different organs such as liver, heart, brain and the like.

The utility model relates to the technical field of neurosurgery cerebral hemorrhage drainage, and discloses a neurosurgery cerebral hemorrhage clinical minimally invasive drainage device which comprises a first drainage tube, a connecting tube is installed on one side of the first drainage tube, a limiting block is fixed to the bottom end of a rotating handle, and a waterproof patch is fixed to the right side of a movable sleeve. And a rubber ring is fixed on the right side of the waterproof patch. When the drainage device is used, the first drainage tube can enter the hematoma position of the brain of a patient through a hole in the brain of the patient, the movable sleeve, the waterproof patch, the rubber ring and other assemblies are arranged on the outer side wall of the first drainage tube, and the first drainage tube is inserted into the head of the patient; the waterproof patch can be attached to the head of the patient through the rubber ring so as to limit the first drainage tube, so that the insertion length of the first drainage tube is controlled, the first drainage tube is stably inserted into the head of the patient according to a certain length, and the problem of rotation is not prone to occurring.

The present application relates to the technical field of machine vision, in particular to a CT image cerebral hemorrhage region segmentation method based on deep learning. The present application obtains a cerebral hemorrhage CT image, labels a cerebral hemorrhage region in the cerebral hemorrhage CT image, establishes a cerebral hemorrhage CT image data set according to the cerebral hemorrhage CT image and the corresponding cerebral hemorrhage region, divides the cerebral hemorrhage CT image data set into a training set and a test set; data augmentation is performed on the training set, and the enhanced picture obtained after data augmentation is added to the training set; the training set is transmitted into a fast subtraction network model and trained to obtain an optimal weight; the test set is transmitted into the fast subtraction network model for testing, and the fast subtraction network model that passes the test is output for cerebral hemorrhage region segmentation. The accuracy of the present application on multiple evaluation indexes is high, and the data augmentation method helps to alleviate the problem of insufficient number of medical image data set images.