Patents
Literature
Patsnap Copilot is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Patsnap Copilot

274 results about "Brain glioma" patented technology

Glioma is a broad category of brain and spinal cord tumors that come from glial cells brain cells that support nerve cells. The symptoms, prognosis, and treatment of a glioma depend on the person’s age, the exact type of tumor, and the location of the tumor within the brain.

Brain glioma segmentation based on cascaded convolutional neural network

The invention discloses a brain glioma segmentation method based on a cascaded convolutional neural network, and the method comprises the steps: carrying out the primary coarse segmentation of a braintumor region, and extracting the approximate position information of a tumor; expanding 10 pixels for each dimension on the basis of coarse segmentation and taking the 10 pixels as input of a fine segmentation network; improviing the fine segmentation network, so as to enable the fine segmentation network to combine the advantages of dense connection, an improved loss function and multi-dimensional model integration; designing an integrated model of three directions (2D, 2.5 D and 3DCNN models), and respectively considering all information of different resolutions corresponding to each direction; integrating post-processing operation condition random fields in a segmentation algorithm, and optimizing continuity of segmentation results in appearance and spatial positions. According to themethod, the brain glioma is segmented through the two-step cascaded convolutional neural network, the advantages of dense connection, a new loss function and multi-dimensional model integration are combined, an integration model in multiple directions is designed, and finally a segmentation result is optimized through a conditional random field.
Owner:NANJING UNIV OF AERONAUTICS & ASTRONAUTICS

Manganese oxide nanoparticle contrast agent for specifically targeting brain glioma

The invention discloses a manganese oxide nanoparticle contrast agent for specifically targeting brain glioma. The manganese oxide nanoparticle contrast agent is prepared by the following steps: dispersing an inorganic manganese compound and sodium oleate into a mixed liquor of ethanol, water and normal hexane, and reacting at 50-70 DEG C to prepare precursor manganese oleate; dissolving the manganese oleate precursor into 1-octadecene, and stirring at 80-100 DEG C under protection of nitrogen; heating to 280-320 DEG C under protection of nitrogen, and refluxing to obtain oleic acid-encapsulated manganese oxide nanoparticles; dispersing the oleic acid-encapsulated manganese oxide nanoparticles into methylbenzene; adding a little of acetic acid, carrying out ultrasonic treatment, and adding a silylating reagent to react, so as to obtain silylanized manganese oxide nanoparticles; dispersing the manganese oxide nanoparticles into deionized water, and bonding specifically targeted molecules of the brain glioma, so as to obtain the manganese oxide nanoparticles for specifically targeting the brain glioma. The manganese oxide nanoparticles disclosed by the invention can be used as a novel nuclear magnetic resonance imaging (MRI) contrast agent for early diagnosis and boundary definition of the brain glioma.
Owner:CAPITAL UNIVERSITY OF MEDICAL SCIENCES

Brain tumor image segmentation method, device and equipment based on deep learning, and medium

The method is applied to the technical field of artificial intelligence, relates to the technical field of blockchain, and discloses a brain tumor image segmentation method, device and equipment basedon deep learning, and a medium. The method includes, in part, the following steps: obtaining a multi-mode brain nuclear magnetic resonance image; preprocessing the brain nuclear magnetic resonance image, so as to obtain a target image with the skull part being removed; and finally, inputting the target image into a preset brain tumor segmentation model, so as to obtain a brain tumor image segmentation result, wherein the preset brain glioma segmentation model is a deep learning model obtained by performing cross validation training according to an adaptive segmentation framework and a brain nuclear magnetic resonance image without a skull part, and the adaptive segmentation framework comprises a plurality of different types of U-Net models and U-Net integrated models. According to the invention, the optimal network structure for prediction in the plurality of models can be automatically selected according to the result of cross validation, and the segmentation performance of the preset brain tumor segmentation model is improved, so the accuracy of brain tumor image segmentation is improved.
Owner:PING AN TECH (SHENZHEN) CO LTD

Method for detecting methylation of brain glioma MGMT promoter gene

The invention discloses a method for detecting the methylation of a brain glioma MGMT promoter gene. The specific steps comprise: extracting the DNA from the brain glioma tissue of a patient by using a tissue DNA extraction kit; carrying out sulfurization treatment on the extracted DNA by using a methylation modification kit; carrying out touchdown PCR on the DNA site template being subjected to the sulfurization modification by using methylation primers represented by SEQ ID NO 1 and SEQ ID 2; diluting the site template 1000 times by using the product obtained through PCR amplification with the methylation primers represented by SEQ ID NO 1 and SEQ ID 2, and carrying out common PCR amplification with primers represented by SEQ ID NO 3 and SEQ ID 4; carrying out 1% agarose gel electrophoresis on the product obtained through the common PCR amplification with the primers represented by SEQ ID NO 3 and SEQ ID 4; recovering the target strip from the 1% agarose gel electrophoresis strips by using an agarose gel recovery kit; carrying out linking transformation on the PCR product and a T carrier, and carrying out blue-white screening; screening recon through bacterial colony PCR; sequencing the positive clones; and analyzing the sequencing results by using biq-analyzer software. The method of the present invention has advantages of high detection accuracy, convenient use, and the like.
Owner:安徽安龙基因科技有限公司

Brain targeted liposome preparation of <99m>Tc tumor imaging medicament and application thereof

The invention discloses a brain targeted liposome preparation of a <99m>Tc tumor imaging medicament and application thereof. In the invention, the idea that an active brain targeted liposome entraps the <99m>Tc tumor imaging medicament is put forward, and the brain targeted liposome preparation of the <99m>Tc tumor imaging medicament is prepared by a fast film dispersion method, wherein liposome has the entrapment rate of over 99 percent, the particle size of less than 30 nm and a structure shown in figure 1. Phospholipid is dispersed in water to form single-layer or multi-layer microcapsules; the liposoluble <99m>Tc medicament is inserted into a bimolecular lipid membrane; and a bradykinin analogue RMP-7 is spread on the surface of the liposome as an active brain targeted directing molecule. Mouse tissue distribution experiments show that the preparation greatly improves the capability of the <99m>Tc medicament in passing through BBB; the SPECT imaging and self-development results of a model of mice with C6 brain gliomas show that the active targeted liposome preparation can realize the early diagnosis of brain tumors when applied to the <99m>Tc tumor imaging medicament; and the brain targeted liposome preparation belongs to the technical field of radiopharmacy and medicinal preparations.
Owner:BEIJING NORMAL UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products