174 results about "Brain gliomas" patented technology

The invention provides a brain glioma segmentation method and system based on a region of interest combined with artificial intelligence, and relates to the technical field of image segmentation, and the method comprises the steps: carrying out the preprocessing of a brain magnetic resonance image; extracting image features by using a multi-scale convolutional neural network; calculating an attention weight to generate a thermodynamic diagram, and binarizing to obtain a candidate region; adaptively adjusting convolution kernel parameters according to the size of the candidate region, extracting multi-scale features by adopting spatial pyramid pooling, and fusing the multi-scale features; semantic segmentation is carried out through a segmentation module; and marking a brain glioma area. According to the method, the accuracy and efficiency of brain glioma segmentation are improved, and the consumption of computing resources is reduced.

The invention relates to the field of medical image processing and pathological diagnosis, aims to solve the problems that brain glioma multi-modal image fusion precision is low, heterogeneity feature and pathological association is weak, and visualization readability is poor, and provides a visualization method and device. The method comprises the steps of multi-modal image preprocessing and registration, regional adaptive multi-modal fusion, pathology association type heterogeneity feature quantification, multi-dimensional pathology visualization, and result verification and optimization. Images are rigidly registered and aligned through mutual information, features are enhanced by adopting a regional differentiation attention fusion algorithm, features are quantified through an improved LSSVM, pathological gold standards are associated, and a three-dimensional visualization model is constructed to visually present heterogeneity information. The device comprises a memory and a processor and can execute the method. According to the method, the heterogeneity evaluation accuracy and clinical readability are improved, treatment scheme optimization is assisted, and the method is suitable for accurate diagnosis and treatment scenes of brain glioma.

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

The invention particularly relates to a curcumin delivery system based on small extracellular vesicles, a preparation method and application. Curcumin has the defects of poor water solubility, poor chemical stability and insufficient targeting, in order to improve the bioavailability of curcumin, the curcumin delivery system based on small extracellular vesicles provided by the invention adopts RGD peptide surface modified sEVs as a carrier to coat curcumin, and saponin is used for assisting ultrasonic drug loading, so that the drug loading rate of curcumin is improved. According to verification of the invention, the delivery system can effectively improve the in-vitro release performance of the curcumin preparation and realize controlled release and slow release. Meanwhile, the delivery system effectively improves apoptosis induction of curcumin to glioma cells, the blood-brain barrier penetrating capacity of the curcumin delivery system is improved, and the treatment effect on brain glioma is expected to be improved.

The invention relates to a CSF1R prediction method in brain glioma, a storage medium and a device, and belongs to the technical field of medical information analysis. The method comprises the following steps: preprocessing magnetic resonance image data; extracting a radiomics feature CR of the magnetic resonance image data; performing multi-angle and multi-slice 2D image analysis and processing on the magnetic resonance image data, inputting the processed data into a convolutional neural network for training, and extracting a deep learning feature DL of the last convolutional layer; fusing the radiomics feature CR and the deep learning feature DL to obtain a feature S; and inputting the feature S into a pre-trained machine learning ensemble learning strategy, performing CSF1R label prediction, and finally obtaining a CSF1R prediction result. According to the method, the end-to-end automatic process is realized, the advantages of multi-modal data, radiomics and deep learning are combined, the prediction accuracy and efficiency are remarkably improved, and powerful support is provided for diagnosis and treatment of brain glioma.

The invention relates to the technical field of biological information, in particular to a brain glioma microenvironment formation key molecular mechanism analysis method, which comprises the following steps: calling expression data to analyze a cell marker sequence to construct a segmentation interval, calculating a candidate factor expression direction to judge trend consistency, identifying expression aggregation difference to construct a split node section, and constructing a subsection; according to the method, partitions are constructed on the basis of marker expression syn-position, judgment is carried out in combination with candidate factor expression directions and marker trends, factor collaboration features are constructed according to the number of trends consistent times, and the semantic sorting information is generated by analyzing the channel change trends to generate drift scores, evaluating multi-label output stability screening key factors and analyzing literature word order positions. Identifying and expressing an aggregation and split structure, guiding a functional pathway to perform trend analysis in a scoring interval and construct a dynamic trajectory, judging label stability and empowerment according to pathway scoring difference, and determining a factor semantic position in combination with a literature word order structure to realize integrated support of regulation and control information and literature evidence.

The invention relates to a planning method, device and equipment for treating brain glioma through multi-fiber laser ablation. The method comprises the following steps: according to pre-acquired image information of a target patient and a segmentation result of a tumor region, sequentially performing segmentation sampling processing on the image information to obtain a candidate optical fiber path set; screening the candidate optical fiber path set according to an optical fiber planning objective function and an optical fiber planning constraint condition to obtain an intermediate optical fiber path set, and determining the number of optical fibers required by tumor ablation according to the intermediate optical fiber path set; determining a target optical fiber path set from the intermediate optical fiber path set according to the number of optical fibers required by tumor ablation and a predetermined path evaluation score; the target optical fiber path set at least comprises position information corresponding to each target optical fiber path. The method can improve the tumor ablation rate and reduce the use of optical fibers.

The invention discloses a brain glioma intestinal microbial marker, a product and application of the brain glioma intestinal microbial marker, and belongs to the field of biological medicine. The invention relates to an enteric microbial marker, which is characterized by being prepared from one or more of Eubacter algenti, Prevotella copri, Alistipes finegili, Bifidobacterium adolescentis and Citrobacter sp., and the enteric microbial marker is prepared from one or more of Eubacter algenti, Prevotella copri, Alistipes finegili, Bifidobacterium adolescentis and Citrobacter sp., and the enteric microbial marker is prepared from one or more of Eubacter algenti, Prevotella copri, Alistipes finegili, Bifidobacterium adolescentis and Citrobacter sp. The invention provides a kit which comprises a detection reagent for detecting the relative abundance of the intestinal microbial marker. The invention provides a product for diagnosing brain glioma and a computer program product related to the brain glioma. The product provided by the invention has good feasibility and accuracy, and provides a new tool for clinical diagnosis.

The invention relates to the technical field of biological medicine, in particular to a nano-vesicle for targeted brain glioma metabolic immune remodeling and a preparation method and application thereof. According to the nano-vesicle for targeted brain glioma metabolism immune remodeling, double-target metabolism and cascade responsive cleavage site modified biological vesicles are integrated, and effective penetration of a drug blood brain barrier and precise targeting of brain glioma can be achieved. The ROS responsive nanoparticles II are prepared by selecting BSA as a drug carrier, applying a nanoprecipitation method and utilizing SLC1A5, LDHA antagonists and responsive linkers, so that the metabolic double-target inhibitor only responds to specific ROS of tumor cells, and specific release in the tumor cells is realized. The cascade response polypeptide provides a simple and convenient delivery scheme with low invasiveness and application prospects for treatment of brain glioma, and is expected to realize precise and individualized treatment in the field of treatment of malignant glioma.

The invention provides a brain glioma CT-MRI (Computed Tomography-Magnetic Resonance Imaging) multi-modal fusion intelligent grading method and a brain glioma CT-MRI multi-modal fusion intelligent grading system, and relates to the field of medical image processing and intelligent diagnosis, and the method comprises the following steps: obtaining CT image and MRI image data of a brain glioma patient through a medical image acquisition device, carrying out standardized preprocessing on the CT image and the MRI image data, and generating a preprocessed image data set; and spatial alignment is carried out on the preprocessed image data set, CT-MRI registration image data are output, and a multi-scale registration method is adopted for spatial alignment. According to the CT-MRI multi-modal fusion intelligent grading method and system based on the brain glioma, by providing the CT-MRI multi-modal fusion intelligent grading method, the problem that in the prior art, image registration and feature fusion are not accurate is solved. A multi-scale registration method and a weighted combined feature extraction mode are adopted, accurate registration of CT and MRI images and efficient fusion of features are ensured, and therefore the accuracy and stability of a grading model are improved.

The invention discloses a brain glioma image segmentation method based on deep learning, and relates to the technical field of image processing. Comprising the following steps: acquiring a multi-modal MRI image and preprocessing the multi-modal MRI image to obtain a multi-channel input image tensor; inputting the multi-channel input image tensor into a feature extraction module to obtain a first loss; establishing an improved UNet model, training the improved UNet model by using a multi-channel input image tensor to obtain a second loss, and adjusting parameters of the improved UNet model in combination with the first loss and the second loss to obtain a trained model; the improved UNet model is based on the UNet model, an improved hypergraph convolution module is introduced into the deepest layer of the UNet model, a multi-scale dynamic weighted feature pyramid module is introduced in a jump connection stage, and a double attention mechanism is introduced in a feature recovery stage; and taking a to-be-segmented brain glioma image, and segmenting the to-be-segmented brain glioma image by using the trained model. According to the method provided by the invention, the segmentation precision and accuracy are greatly improved.

The invention discloses a brain glioma organ chip with adjustable tumor microenvironment gradient and a method for mediating formation of brain glioma organoid by the brain glioma organ chip, and belongs to the technical field of organ chips. The preparation method comprises the following steps: firstly, preparing a glioma organ chip with adjustable tumor microenvironment gradient by utilizing a prepolymer solution containing glioma cells and vascular endothelial cells and a prepolymer solution containing biochemical molecules; then, the obtained brain glioma organ chip with the adjustable tumor microenvironment gradient is subjected to three-dimensional dynamic co-culture under the perfusion condition, three-dimensional culture and co-culture of brain glioma cells and vascular endothelial cells are achieved at the same time, endothelial-glioma multicellular tumor spheres are formed, and construction of brain glioma organs is achieved. The brain glioma organoid established by the invention successfully summarizes key characteristics of a tumor microenvironment, including biophysical factors simulated by physiological fluid and biochemical factors of three-dimensional culture microgel with adjustable concentration gradient of biochemical molecules.

The invention relates to a brain glioma grading method based on multi-instance causal characterization learning, and the method comprises the following steps: S1, data preprocessing, S2, feature extraction through ResNet-50, S3, feature coding of high-dimensional feature representations of instances, S4, decoupling of low-dimensional feature representations of each instance, obtaining causal features and non-causal features, and carrying out classification on the causal features and the non-causal features. S5, constructing an adaptive adjacency matrix A, constructing a sparse adjacency matrix A (k) by adopting a Topk neighbor selection strategy, and carrying out information aggregation through a graph neural network to obtain aggregation features; S6, carrying out local feature aggregation on each scanning plane p, calculating a weight weighted p of each scanning plane by utilizing a full-connection network, and carrying out weighted fusion to obtain an aggregation feature; s7, fusing and grading the aggregated features and the features; the method has the advantage of improving the stability and clinical applicability of the grading model.

The invention discloses a brain glioma classification method and device based on multi-mode MRI, and relates to the technical field of image processing. According to the method, multiple tumor sub-regions of the brain glioma are acquired based on a to-be-processed multi-modal MR image, multiple local ROIs are extracted based on the multiple tumor sub-regions, and then the sub-type of the brain glioma is determined based on the multiple local ROIs and a global ROI. The subtype can be determined through the multi-modal MR image, so that on one hand, non-invasive identification of the subtype is realized, and bleeding and infection risks caused by identification of the subtype are avoided; and on the other hand, the classification accuracy can be improved by utilizing complementary information between different modal images and a boundary form between different tumor sub-regions. Besides, through the fine structure features of each tumor sub-region reserved from a plurality of visual angles by the plurality of local ROIs, and in combination with the spatial distribution context information of the whole brain glioma provided by the global ROI, a better balance between the processing precision and the calculation efficiency can be realized.

The invention belongs to the field of tumor drugs, and particularly relates to application of an adeno-associated virus vector overexpressing Semaphorin 3G in preparation of drugs for treating brain glioma. The AAV-SEMA3G can effectively reduce the growth speed of brain glioma of mice and prolong the survival time of tumor-bearing mice, and can be particularly used for preparing drugs for treating brain glioma and the like. The invention discloses an application of AAV-SEMA3G in preparation of a medicine for treating brain glioma.

The application discloses a kind of nanomaterial and its preparation method and application, the nanomaterial includes exosome and liposome;The exosome expresses immune checkpoint, the exosome is derived from brain glioma cell;The liposome is loaded with I type photosensitizer.The application is by PDT, immune checkpoint and brain glioma cell exosome antigen three tubes simultaneously to remodel tumor local immune microenvironment, greatly improve the efficiency of cancer immunotherapy, can activate strong anti brain glioma immune response and overcome immune escape.

The invention relates to a brain glioma auxiliary decision-making method based on terahertz signals. The brain glioma auxiliary decision-making method comprises the following steps: carrying out terahertz spectrum detection on brain glioma of different pathological levels to obtain terahertz spectrum data; converting the terahertz wave spectrum data of each wave band into pixel points, and arranging the pixel points according to a preset sequence to obtain a terahertz wave spectrum image; extracting a characteristic value of the terahertz wave spectrum image; inputting the characteristic value of the terahertz wave spectrum image as a training sample into a deep learning model for training to obtain a brain glioma pathology level prediction model; and predicting the pathological level of the target brain glioma by using the brain glioma pathological level prediction model to obtain a prediction result. According to the method, the terahertz spectrum data is converted into the image, the features are extracted, and the deep learning model is combined, so that key features for distinguishing different pathological levels can be automatically learned from a complex spectrum mode, multi-scale and multi-angle comprehensive analysis is realized, and the accuracy of predicting the pathological level of the brain glioma is improved.

The application belongs to the technical field of medicine production, and particularly relates to a preparation method and application of five deuterium-substituted glucose. The method comprises deuterium substitution of D-methyl glucoside, and demethylation of the deuterium-substituted D-methyl glucoside to obtain a target product, namely [2,3,4,6,6'-d5]-D-glucose. The preparation method of the five deuterium-substituted glucose is simple in process route, convenient to operate, mild in experimental conditions, and the synthesized five deuterium-substituted glucose is successfully applied to the description of glycolysis metabolism in a brain glioma model, which is helpful to the clinical conversion application of metabolic imaging technology.

This invention relates to the field of microfluidic chip technology, specifically to a dynamic microfluidic chip device, its preparation method, and its applications for studying CAR-T therapy for gliomas. The preparation method includes: fabrication of the microfluidic chip; reconstruction of neural tissue; reconstruction of the blood-brain barrier; and simulation of the glioma microenvironment. The dynamic microfluidic chip device includes a microfluidic chip; the microfluidic chip includes, from left to right, a vascular channel, a brain parenchyma channel, a tumor channel, and a subarachnoid channel; each of the vascular channel, brain parenchyma channel, tumor channel, and subarachnoid channel includes a cell culture chamber with an inlet on one side; the cell culture chambers of the vascular channel and the subarachnoid channel have corresponding outlets on the other side. The applications include: CAR-T cell infusion; observation of transmembrane migration; and detection of biomarkers. This invention, through the dynamic microfluidic chip device, its preparation method, and its applications, aims to achieve more accurate in vitro evaluation of CAR-T cell therapy.

The application belongs to the technical field of biological medicine, and particularly relates to application of a compound Merulin A in preparation of an anti-glioma drug. The application provides application of the compound Merulin A in preparation of the anti-glioma drug. Experiments prove that the compound Merulin A exhibits significant anti-glioma activity, can effectively promote early apoptosis and cell necrosis of glioma cells, and further inhibit proliferation and migration of the glioma cells. Moreover, due to advantages of wide source, simple extraction process, short cycle and low cost, the compound Merulin A has a wide application prospect as the anti-glioma drug.

The application discloses a polypeptide ligand for brain glioma diagnosis and preparation and application of a radioactive molecular probe. The polypeptide targeting a TREM2 protein has the amino acid sequence as shown in the following: HLRKLRKR. The targeted polypeptide designed by the application has the characteristics of small molecular weight, strong blood brain barrier penetration and strong TREM2 protein binding capacity. The radioactive nuclide labeled molecular probe prepared by the application has the characteristics of strong targeting and easy observation as a brain glioma imaging drug, and is convenient for clinical application. The application improves the diagnosis effect of brain glioma and provides a new idea for early discovery and early treatment of brain glioma.

This application discloses a deep learning method, apparatus, device, and storage medium for expert knowledge-constrained glioma grading. The method includes: constructing radiomics labels that include expert knowledge; constructing a training model for discrete distance-constrained glioma grading; and inputting the radiomics labels into the glioma grading model to complete parameter optimization. The above-mentioned solution provided by this application has good grading performance and high clinical usability in the glioma grading task, thereby reducing the workload of doctors in clinical use and enabling the model to more efficiently utilize patients' brain magnetic resonance imaging data.

The invention discloses a borneol modified erythrocyte membrane coated dendritic macromolecule bionic nano drug delivery system and preparation and application thereof, the bionic nano drug delivery system comprises an erythrocyte membrane and a drug loaded dendritic macromolecule coated in the erythrocyte membrane, the surface of the erythrocyte membrane is modified with targeted molecule borneol, the drug is an anti-tumor drug, such as bufotalin. In combination with a nasal drop administration mode, not only can the brain targeting efficiency of the glioma treatment drug be improved, but also the glioma treatment drug has immune escape and tumor microenvironment response capabilities, the in-vivo circulation time of the drug is effectively prolonged, and the glioma treatment effect is further improved. The design that the dendritic macromolecules are coated with the modified erythrocyte membranes combines the biocompatibility of natural cell membranes and the multifunctionality of nanoparticles, and the dendritic macromolecules have huge application potential in the fields of drug delivery, immune regulation, detoxification, targeted therapy and the like.

The present invention relates to a preparation method and application of neutrophil-targeted biofilm-loaded drug nanoparticles, which can effectively solve the problem that it is difficult to cross the blood-brain barrier in the prior art. The technical solution adopted is to construct a pET-30a(+)-inaX-N-angiopep-2 recombinant plasmid expression vector and transform it into E.coil BL21(DE3) competent cells to obtain a recombinant strain. The recombinant strain is spread on an LB solid agar medium and cultured overnight. A single colony is picked into an LB broth medium and induced with isopropyl- β -D-thiogalactoside. After verifying the expression of the Angiopep-2 polypeptide, the bacterial cell precipitate is digested with lysozyme, and after ultrafiltration and centrifugation, an Angiopep-2 biofilm is prepared; PEI and CpG are incubated, and Tris-HCl and dopamine hydrochloride powder are added to obtain PDA-PEI-CpG; then the Angiopep-2 biofilm and PDA-PEI-CpG are incubated to obtain the desired product. The neutrophil-targeted biofilm-loaded drug nanoparticles prepared by the present invention solve the problems such as the difficulty in penetrating the blood-brain barrier in the treatment of glioblastoma with drugs, are simple and convenient to operate, and have broad application prospects.

The invention relates to a multi-modal medical image deep learning enhanced segmentation system and a method thereof, belongs to the field of medical image processing, and aims to solve the problem of inaccurate brain glioma target region boundary segmentation. According to the technical scheme, the method comprises the steps that a metabolic domain PET image and a structural domain MRI-T2 image are obtained, and image registration, noise suppression and intensity standardization preprocessing are carried out; glycolysis features and texture anisotropy features are extracted through a double-domain feature decoupler; constructing a graph neural network to generate a metabolism-structure interaction graph; calculating a pathological infiltration confidence coefficient thermodynamic diagram based on the atlas; the thermodynamic diagram is used for self-adaptive radiotherapy dose segmentation, and the dose gradient is dynamically adjusted; and finally outputting the tumor target boundary.

The invention discloses a model, a method, an electronic device and a medium for MRI brain glioma segmentation, and the model comprises a learnable bias field correction module which is used for adaptively estimating and correcting a low-frequency bias field in an original brain glioma MRI image; the multi-resolution feature extraction module is used for carrying out multi-resolution feature extraction and outputting a multi-resolution feature graph group containing different resolution features and shallow layer features; the multi-resolution feature fusion module is used for carrying out feature fusion on the multi-resolution feature map group and recovering relatively high resolution to obtain deep features; and the statistical space gating fusion module is used for receiving the deep layer features and the shallow layer features, performing feature fusion through channel statistical screening and a space attention gating mechanism, and outputting an MRI brain glioma segmented image. The technical problems that an existing brain glioma MRI image segmentation method is generally poor in adaptability, insufficient in boundary continuity, low in fusion efficiency and poor in global and local feature balance are solved.

The present invention discloses a drug for treating brain gliomas and a method for preparing the drug, relating to the field of biomaterials. By combining the advantages of bacteria, natural exosomes, and synthetic liposomes, the present invention prepares a modular bacterium consisting of a blood-brain barrier targeting module, a photothermal module, and a ROS consumption module. The drug exhibits excellent blood-brain barrier crossing, targeting, photothermal conversion, and ROS consumption capabilities, enabling brain-targeted delivery, increasing tumor antigens, and reducing excess ROS in the tumor microenvironment, further enhancing the efficacy of immune checkpoint inhibitors against brain gliomas.

The present invention belongs to the field of biomedicine technology and specifically relates to the use of a natural product, Oxirapentyn A, in the preparation of anti-glioma drugs. The natural product, Oxirapentyn A, has significant anti-glioma activity and can inhibit the proliferation, migration, and invasion of glioma cells by promoting early and late apoptosis of glioma cells, showing excellent potential as an anti-glioma drug. Furthermore, the natural product, Oxirapentyn A, can be directly prepared through large-scale fermentation of marine fungi or obtained by simple derivatization of the fermentation product, Oxirapentyn B. It has a wide source, a simple production process, a short cycle, and low product cost, and has broad application prospects.

The invention discloses a preoperative brain glioma image segmentation method and system, and relates to the technical field of medical image processing, and the method comprises the steps: receiving brain glioma multi-mode MRI image data, carrying out the preprocessing of the brain glioma multi-mode MRI image data, and obtaining the processed MRI image data; wherein the modality of the multi-modal MRI image data of the brain glioma comprises one or more of T1, T1ce, T2 and FLAIR; the processed MRI image data are input into a pre-trained nnU-SWMama brain glioma segmentation model, a three-dimensional automatic segmentation result of the brain glioma is output and obtained, the three-dimensional automatic segmentation result of the brain glioma comprises a tumor core and an enhanced tumor area, the three-dimensional automatic segmentation result of the brain glioma is exported, and the three-dimensional automatic segmentation result of the brain glioma is obtained. The accuracy of brain glioma segmentation can be effectively improved.

This invention discloses a method for glioma identification with flexible access control and privacy protection, belonging to the field of medical artificial intelligence and privacy computing. The method includes: secure initialization and fine-grained access control configuration; local training and dynamic parameter updates through bidirectional comparative learning on each client, and selection of the optimal model as a reference source based on a dynamic validation set to achieve cross-site parameter alignment; encryption and signing of uploaded parameters, and secure aggregation on the server side to complete global model iterative updates. The fine-grained access control employs attribute-based encryption based on complex attribute predicates to achieve precise authorized access to model parameters, combines symmetric and homomorphic encryption to protect privacy during transmission and aggregation, and provides verifiability through digital signatures. This invention can achieve stable and rapid convergence in both IID and non-IID scenarios, improving classification accuracy and efficiency, while effectively reducing the risk of leakage in parameter interaction and storage.