95 results about "Cerebral Tumor" patented technology

The invention relates to a MR brain tumor image segmentation method based on an improved full-convolution neural network algorithm. The method comprises the following steps: step 1, image preprocessing; step 2, improved FCNN coarse segmentation algorithm, including based on a FCNN, adding a batch regularization layer after each convolution layer to speed up training of the network and improve precision of a model, and performing features fusion on pooled brain tumors features for three times, to obtain more refined brain tumors features, and establishing an improved FCNN, called a FCNN-4s network; step 3, FCNN-4s and CRF resegmentation fusion algorithm, including initializing an energy function in a CRF model according to a FCNN-4s coarse segmentation result in the second step, to obtain aprobability value of pixel original home label, and then calculating the CRF model by the following steps, continuously iterating and correcting two kinds of probability maps of FCNN-4s prediction, to obtain a CRF resegmentation fusion result.

Pharmaceutical composition comprising antibodies or antigen binding fragments thereof that bind to stage-specific embryonic antigen 4 (SSEA-4) are disclosed herein, as well as methods of use thereof. Methods of use include, without limitation, cancer therapies and diagnostics. The antibodies of the disclosure can bind to certain cancer cell surfaces. Exemplary targets of the antibodies disclosed herein can include carcinomas, such as breast cancer, lung cancer, esophageal cancer, rectal cancer, biliary cancer, liver cancer, buccal cancer, gastric cancer, colon cancer, nasopharyngeal cancer, kidney cancer, prostate cancer, ovarian cancer, cervical cancer, endometrial cancer, pancreatic cancer, testicular cancer, bladder cancer, head and neck cancer, oral cancer, neuroendocrine cancer, adrenal cancer, thyroid cancer, bone cancer, skin cancer, basal cell carcinoma, squamous cell carcinoma, melanoma, and / or brain tumor.

The present invention is solid tumor treating medicine composition and belongs to the field of medicine technology. The medicine composition contains melphalan in effective anticancer amount and medicinal supplementary material. The medicinal supplementary material is mainly biocompatible, degradable and absorbable polymer, and during the degradation and absorption of the polymer, melphalan is released slowly to local tumor part to lower the systemic toxic reaction and to maintain local medicine concentration. The present invention has enhanced treating effect. The solid tumor includes cerebral tumor, liver cancer, lung cancer, esophagus cancer, gastric cancer, etc.

The invention relates to a preparation method and application of targeted co-supported drug delivery system nano-particles based on polylactic-co-glycolic acid (PLGA), which can effectively solve the problem of preparing the targeted co-supported drug delivery system nano-particles based on polylactic-co-glycolic acid, and realizes the application in cerebral tumor targeted treatment medicines. The method comprises the following steps: connecting Angiopep-2 by utilizing the reactive amino group on chitosan: reacting chitosan with 3-maleimidopropionic acid N-hydroxysuccinimide to enable the amino terminal of chitosan to have maleimide; reacting with terminal-sulfhydrylated Angiopepe-2 to obtain a chitosan-angiopep-2 polymer. The polymer can be applied to preparation of a PLGA-based targeted co-supported drug delivery system. The method is stable and reliable, the product has a good using effect, small-molecular chemical drugs and genetic drugs can be delivered at the same time, or a fluorescent probe can pass through a blood brain barrier and enters the brain while chemotherapeutic drugs are delivered, and targeted cerebral tumor treatment can be synergized or targeted cerebral tumor treatment and diagnosis can be integrated into a whole.

The invention discloses an application of a compound as a JAK-STAT3 signal passage inhibitor, and particularly relates to an application of a compound with a formula I or pharmaceutically acceptable salt of the compound in the process of preparing an anti-tumor medicament. The application provides a novel treating candidate medicament for a tumor patient, thereby probably further improving the treatment effect on the patient and improving the prognosis of the patient. The compound with the formula I or the pharmaceutically acceptable salt of the compound has the effect on various tumor cells, which indicates that the compound can be used for treating various cancers including cerebral tumor, genitourinary system tumor, lymphatic system tumor, stomach cancer, laryngeal cancer, nasopharyngeal cancer, skin cancer, bone cancer, blood cancer, leukemia, breast cancer and histiocytic lymphoma, non-small cell lung cancer, small-cell lung cancer, lung adenocarcinoma, lung squamous cell cancer, pancreatic cancer, prostatic cancer, liver cancer, epithelial cell cancer and the like. The definition of genes in the formula refers to description for details.

The invention discloses injection of mannite and glycerol, which contains mannite, glycerol and water for injection. Furthermore, the invention also discloses a method for preparing the injection, which comprises the following steps: taking the mannite and the glycerol, dissolving into the water for injection, filtering and filling. The injection of the mannite and the glycerol is clinically used for treating cerebrovascular diseases, brain trauma, cerebral tumors, intracranial inflammation and the diseases of acute and chronic intracranial hypertension, hydrocephalus and the like caused by other reasons. The injection of the mannite and the glycerol has the functions of lowering the intracranial pressure quickly and eliminating the hydrocephalus and can also avoid death because of acute renal failure caused by the injury of the kidney; the injection of the mannite and the glycerol suppresses the apoptosis of neural cells and achieves the function of protecting the brain; the function of lowering the intracranial pressure is stable and has long retention time; crystals occurring because of the change of the air temperature or in the processes of storage and transportation are eliminated; and the glycerol is used as a caloric agent and can improve and recover the energy metabolism of the important viscera of the heart, the brain, the kidney and the like during oxygen deficiency. The injection of the mannite and the glycerol is a very effective, stable and safe medicine for promoting urination and removing water clinically.

A method and system for classifying tissue endomicroscopy images are disclosed. Local feature descriptors are extracted from an endomicroscopy image. Each of the local feature descriptors is encoded using a learnt discriminative dictionary. The learnt discriminative dictionary includes class-specific sub-dictionaries and penalizes correlation between bases of sub-dictionaries associated with different classes. Tissue in the endomicroscopy image is classified using a trained machine learning based classifier based on the coded local feature descriptors encoded using a learnt discriminative dictionary.

A brachytherapy apparatus and method are provided for treating tissue forming an internal body cavity, such as an excised breast or brain tumor bed. The apparatus has at least one outer wall that is movable between (i) a retracted position spaced inwardly relative to tissue forming the internal body cavity, and (ii) an expanded position spaced outwardly and contiguous to tissue forming the internal body cavity. The outer wall is formed by a stent, a balloon catheter, or a plurality of axially-elongated solid or hollow flexible members that are angularly spaced relative to each other. A plurality of radiation sources are carried by the at least one outer wall and movable therewith between the retracted and expanded positions for transmitting radiation in the expanded position into the tissue forming the internal body cavity.

The invention belongs to the technical field of brain tumor scalp positioning image processing, and discloses a brain tumor scalp positioning image processing method and system. The brain tumor scalppositioning image processing system comprises a brain image acquisition module, a main control module, an image enhancement module, an image segmentation module, a classification module, a tumor labeling module, a scalp positioning module and a display module. According to the invention, automatic segmentation is carried out on the MRI brain tumor image by using existing data set resources and related computer vision, machine learning and deep learning technologies through the image segmentation module, so that the workload of doctors can be effectively reduced and the segmentation efficiencycan be improved; meanwhile, the brain tumor position is positioned through the scalp positioning module and the medical positioning mechanism, the tumor position can be accurately positioned, the success rate of an operation is increased, the working efficiency is improved, and the workload of medical staff is reduced.

The invention relates to a brain tumor segmentation algorithm based on combination of deep learning and a traditional segmentation algorithm, in particular to a full-connection CRF cascaded FCN and Kmean value brain tumor segmentation algorithm. The DenseCRF matches all the pixels in the original image with each pixel in the segmentation result of the FCN algorithm, finds the pixels with the sameattribute, supplementarily smoothes the input, improves the detail information of the segmentation result, and improves the segmentation precision. Meanwhile, in different segmentation algorithms, the segmentation standards are different, and the segmentation results obtained based on the algorithms of the different segmentation standards are complementary to each other by fusing the deep learning algorithm FCN with the different segmentation standards and the traditional segmentation algorithm K-means clustering, so that the segmentation results are closer to real segmentation images. Therefore, the brain tumor nuclear magnetic resonance image is segmented more accurately, and a more accurate tumor image is provided for high-precision repetitive measurement and evaluation of the brain tumor nuclear magnetic resonance image.

The invention discloses a nanometer drug delivery system targeted for brain tumors and tumor stem cells thereof. The nanometer drug delivery system comprises tumor treatment drugs, a carrier frameworkand targeting molecules combined to the surface of the carrier framework, wherein the carrier framework is a cationic liposome; the targeting molecules at least comprise a first targeting molecule and a second targeting molecule, the first targeting molecule is surface modification polypeptide, and the second targeting molecule is an aptamer; and the tumor treatment drugs are selected from chemotherapy drugs and / or gene targeting drugs. The invention discloses a preparation method and application of the nanometer drug delivery carrier. The nanometer drug delivery carrier can carry and load target genes or chemotherapy drugs for cerebral tumor treatment, and through dimolecular modification, the targeting efficiency of the system is improved to 67% or above from 5% which is obtained underthe condition that modification is not performed.

The invention provides a traditional Chinese medicine composition, which consists of raw materials in the following weight portion: hirudo, gadfly, eupolyphaga, angelica, radix paeoniae rubra, ginseng, radix astragali, peach kernel, oyster, semen vaccariae, radix curcumae, rhizoma corydalis, radix bistortae, amomum fruit, and angelica dahurica. The invention also provides a traditional Chinese medicine preparation containing the composition and a method for preparing the same. The traditional Chinese medicine composition and the traditional Chinese medicine preparation are mainly used for treating cerebral apoplexy, cerebral infarction or cerebral tumor which is distinguished to belong to Qi-deficiency and blood stasis syndrome by the traditional Chinese medical science.

The invention discloses a cascaded UN Net brain tumor segmentation method combined with wavelet transform. The method comprises the following steps: S1, preprocessing an input image sequence; wherein the image sequence comprises four modal data FLAIR, T2, T1 and T1C and annotation data; s2, establishing a first layer of a cascaded network by using a Pytch deep learning framework, training a UNet model combined with wavelet transform, and then multiplying a training result of the model by the modal data T1 and T1C to generate a coarse segmentation image; and S3, establishing a second layer of the cascaded network by using a Pytch deep learning framework, training the NNet model combined with wavelet transform, and generating a fine segmentation image, namely a final brain tumor segmentation result. According to the method, the segmentation efficiency can be improved, and the problems of fuzzy tumor boundary, low segmentation precision and the like in brain tumor MRI segmentation can be solved.

The invention discloses a three-dimensional MRI brain tumor segmentation method based on deep learning, and the method comprises the following steps: S1, carrying out the preprocessing of three-dimensional MRI brain data, dividing a data set, and enabling the data set to meet the input conditions of a model; s2, a deep convolutional neural network is constructed and trained, a network framework adopts the form of an encoder and a decoder, and a multi-scale convolution joint module and a global context aggregation module are added; and S3, post-processing the obtained prediction data to further improve the segmentation effect. According to the segmentation method provided by the invention, the low-level features and the high-level features of the segmentation object are combined, the multi-scale information and the global context information are effectively fused, and the influence of the learned redundant features is reduced, so that the segmentation result of the brain tumor is improved.

The invention discloses a MRI (Magnetic Resonance Imaging) image segmentation method based on fuzzy thought and a level set frame, and mainly solves the problem of segmentation errors and low calculation speed generated since an original segmentation method can not overcome an intensity non-uniformity phenomenon or noise interference in the MRI process that the nuclear magnetic resonance image is segmented. The method comprises the following implementation steps: 1) inputting an original nuclear magnetic resonance image; 2) carrying out iterative computation on a magnetic resonance image matrix to solve a membership matrix u corresponding to a magnetic resonance image matrix I; 3) regulating an evolution propulsive parameter, and guaranteeing that the membership matrix u is subjected to exact convergence on a target outline; and 4) representing different areas in the image matrix I with different element values of the membership matrix u to obtain an anticipatory segmentation result. By use of the method, the segmentation process of the nuclear magnetic resonance image can be effectively and quickly finished, an accurate target area can be obtained, and the method can be used for cerebral tumor detection and cancer cell examination in a MRI medical image.

The invention belongs to the field of traditional Chinese medicine for treating tumor and provides a traditional Chinese medicine for treating brain tumor, which aims to achieve good and quick efficacies. The traditional Chinese medicine for treating brain tumor is prepared by the materials such as windpipe trachea, holly root, blackberry lily, glossy ganoderma, angelica, alga, kombu, scolopendra, frankincense, myrrh, borneol, root of pseudo-ginseng, Tianxiong, rehmannia root, herb of yerbadetajo, radix adenophorae and mulberry leaf. The traditional Chinese medicine has efficacies of supporting healthy energy, consolidating constitution, benefiting vital energy, nourishing the blood, promoting blood circulation by dissipate blood stasis, clearing away heat-evil and expelling superficial evils, and has the advantages of obvious and quick efficacies.

The invention discloses an in-situ inoculating operation method for a cerebral tumor tissue block animal. The method comprises the following steps: (a) taking a cerebral tumor tissue, and shearing the cerebral tumor tissue into tumor tissue particles; (b) placing the tumor tissue particles into a needle tube of a tissue block injection needle, and carrying out quantifiable indwelling control on the tumor tissue particles; (c) anaesthetizing the animal, dissecting the skin on the surface of the animal skull, and boring a hole on the animal cranial bone; (d) inserting the tissue block injection needle along a cranial bone hole, and slowly injecting the tumor tissue particles; and (e) slowly pulling out the needle, sealing the cranial bone hole by bone wax, and suturing the scalp. The method can ensure the original tissue structural property of an inoculated tumor tissue, provides a tumor model with high simulation degree for tumor research, can ensure the vitality of inoculated cells, has high tumor transplantation success rate, can realize quantification of cell number in the inoculated tumor tissue and positioning of inoculation in the tumor tissue animal brain, has short operation time, and can meet the requirement of needing large amount of animal models in once experiment.

The invention belongs to the technical field of brain tumor medical image three-dimensional reconstruction, and discloses a brain tumor medical image three-dimensional reconstruction display interaction method and system. The brain tumor medical image three-dimensional reconstruction display interaction system is provided with an image acquisition module, an image correction module, an image extraction module, a central control module, an image processing module, a three-dimensional modeling module, a brain tumor diagnosis module, an analysis module, a scheme generation module, a planning module, an operation interaction module, an image storage module and a display module. The brain tumor medical image three-dimensional reconstruction display interaction method comprises the steps: collecting and correcting a brain tumor image; constructing a brain tumor region three-dimensional model; the brain tumor is diagnosed, and analyzing the three-dimensional model; generating a brain tumor excision scheme, and planning brain tumor excision operation; and executing operations. According to the invention, the three-dimensional model is constructed, the brain tumor operation is simulated through human-computer interaction, a basis is provided for a real operation, and the operation risk is reduced.

The invention relates to the field of antineoplastic medicines and provides a betulinic acid analogue with the structure shown in figure (1) or solvate thereof. The definition of R1, R2, X and n is in the specification. The invention also provides the a preparation method of the betulinic acid analogue with the structure shown in figure (1) or the solvate thereof, and the applications of pharmaceutical compositions containing the betulinic acid analogue or the solvate thereof and medicines using the betulinic acid analogue or the solvate thereof as the effective constituent for preparing antineoplastic medicines for treating pulmonary cancer, prostatic cancer, colon cancer, leukemia, mammary cancer, liver cancer, gastric cancer, pancreatic cancer, malignant neuroglioma, cerebral tumor, and the like.

The invention relates to the field of antineoplastic medicines and provides a betulinic acid analogue with the structure shown in figure (1) or solvate thereof. The definition of R1, R2, X and n is inThe invention relates to the field of antineoplastic medicines and provides a betulinic acid analogue with the structure shown in figure (1) or solvate thereof. The definition of R1, R2, X and n is inthe specification. The invention also provides the a preparation method of the betulinic acid analogue with the structure shown in figure (1) or the solvate thereof, and the applications of pharmaceu the specification. The invention also provides the a preparation method of the betulinic acid analogue with the structure shown in figure (1) or the solvate thereof, and the applications of pharmaceutical compositions containing the betulinic acid analogue or the solvate thereof and medicines using the betulinic acid analogue or the solvate thereof as the effective constituent for preparing antintical compositions containing the betulinic acid analogue or the solvate thereof and medicines using the betulinic acid analogue or the solvate thereof as the effective constituent for preparing antineoplastic medicines for treating pulmonary cancer, prostatic cancer, colon cancer, leukemia, mammary cancer, liver cancer, gastric cancer, pancreatic cancer, malignant neuroglioma, cerebral tumor, andeoplastic medicines for treating pulmonary cancer, prostatic cancer, colon cancer, leukemia, mammary cancer, liver cancer, gastric cancer, pancreatic cancer, malignant neuroglioma, cerebral tumor, andthe like. the like.

The invention provides an SP-FCN-based MRI brain tumor image segmentation system and method. The method comprises the steps of extracting features of brain tumor images in different modes through a superpixel method to obtain ROI segmentation results under different modals; taking ROI images under different modals as the input data of the FCN, carrying out data fusion to obtain a final segmentation result, and taking the ROI images under different modals as the input, so that the calculation amount of the data is reduced, and the final result is more accurate; meanwhile, the difference of white matter lesion images can be more easily captured by adopting multi-mode image fusion than a single-mode image, and the stability of the algorithm can be improved by multiple registration.

The invention relates to a severe tumor image recognition system and method, in particular to a magnetic resonance image two-stage multi-model automatic brain tumor diagnosis system based on brain tumor image big data. The technical problem to be solved by the invention is to provide a set of magnetic resonance image two-stage multi-model automatic brain tumor diagnosis system based on a convolutional neural network, which is used for high-accuracy computer-assisted brain image data analysis by performing information mining, feature extraction and experience learning from historical diagnosisbig data. Diagnosis accuracy is independent of experience of doctors, and meanwhile diagnosis speed is increased.

The invention discloses a brain tumor image segmentation method, system and device and a storage medium. The method comprises the following steps: carrying out preprocessing and data amplification on a brain tumor image and a label; performing convolution and down-sampling on the brain tumor image, and extracting context semantic information in the brain tumor image to obtain a feature map; performing up-sampling on the feature map, and performing feature fusion on the up-sampled map and the features in the encoder module at the same level; aggregating the feature maps through a feature pyramid fusion module, and inputting the aggregated feature maps into an expectation maximization self-attention module to learn global context information; and aggregating the features and the maximum-level feature map to obtain a final semantic segmentation result. Based on a multi-scale channel attention mechanism, feature extraction and feature fusion, global context information is extracted by adopting a feature pyramid and an expectation maximization attention mechanism, the semantic segmentation precision is improved, and the method can be widely applied to the field of computer vision and image processing.

The invention belongs to the traditional Chinese pharmacology field, and concretely relates to a method for constructing the pharmacological mechanism of a Jinlong capsule through a biological and genetic engineering process. The method analyzes the system biology of a processed gene chip result and constructs the pharmacological mechanism of the Jinlong capsule by utilizing a Thomson Reuters Genego database through the hybridization, detection and analysis of the gene chip via omics and the system biology process. The invention also discloses a use of the Jinlong capsule as a brain tumor resistance medicine and in chemotherapeutic drug tolerance activity reversion. And the pharmacological mechanism of the Jinlong capsule as the brain tumor resistance medicine and in the chemotherapeutic drug tolerance activity reversion is constructed through the method.

The present invention relates to one kind of nasal cavity administrated preparation of methotrexate to target to brain. The present invention is suitable for preventing and treating primary and metastatic cerebral tumor, meningeal leukaemia, cerebral infiltration of leukaemia, etc. The preparation contains methotrexate or its medicinal acceptable salt as well as pharmacological acceptable supplementary material. After being administrated, the medicine reaches brain fast and is enriched in brain to produce high disease preventing and treating effect while the medicine density in blood and other tissues is reduced to decrease general side effect, the preparation has also the advantages of fast release and less nasal cilium toxicity.

In some embodiments, a method may include treating brain cancer sensitive to cytotoxic effect. The method may include intraventricularly administering to a subject via a subject's cerebrospinal fluid an effective amount of a pharmaceutical formulation. The pharmaceutical formulation may include at least one chemical compound. In some embodiments, the pharmaceutical formulation may include at least one aqueous diluent. The at least one chemical compound may include a molecular weight of between about 400 MW and about 10,0000 MW. The at least one chemical compound may include protein binding of greater than 30% and greater than 70 Angstroms in cross sectional area. In some embodiments, the at least one chemical compound includes Irinotecan, SN-38, and / or a related derivative thereof. In some embodiments, the method may include ameliorating and / or inhibiting brain cancer in the subject using the pharmaceutical formulation.

The invention belongs to the technical field of image processing, and provides an MRI brain tumor image segmentation method and system based on an improved U-Net network. The method comprises the following steps: acquiring a to-be-segmented MRI brain tumor image, and inputting the to-be-segmented MRI brain tumor image into a trained improved U-Net network to obtain an image marked with a segmented tumor; and, according to the improved U-Net network, a residual module with a double-attention mechanism is introduced to replace a convolutional layer of the U-Net network, an expansion pyramid module with an attention mechanism is introduced into the U-Net network, and the double-attention mechanism is introduced after each layer skips connection.

The invention discloses a brain tumor segmentation method of a deep residual network based on U-Net architecture. The brain tumor segmentation method comprises the following steps: S1, constructing acombined convolution block of the deep residual network; and S2, constructing a branch structure network for implementing the three-branch structure model; and S3, combining to form an integral network of the three-branch structure model. The method has the advantages that the network performance can be more effectively prevented from being reduced, and the network performance can be better improved. Besides, standardizing, cutting and removing the focus-free image data of each modal image data, and finally combining the focus-free image data into multi-channel data. Therefore, experimental results show that the algorithm has advanced performance. Tumor segmentation effect is greatly improved.

The invention belongs to the technical field of traditional Chinese medicine, and particularly relates to application of lawn pennywort herb liver-healing tablets in preparation of a drug for inhibiting cell proliferation of cerebral tumor cells SF767 and a preparation method of the lawn pennywort herb liver-healing tablets.The lawn pennywort herb liver-healing tablets are prepared from 699 g of lawn pennywort herb, 1,398 g of herba pimpinellae, 699 g of creeping woodsorrel herb and 209 g of brooklet anemone roots.The lawn pennywort herb liver-healing tablets are prepared by means of supercritical extraction, and the content of oleanolic acid is greatly increased.