146 results about "Carcinogenesis" patented technology

The invention discloses a colorectal cancer focus segmentation method based on improved TransUNet. The method comprises the following steps: collecting related pathological image data of a colorectal cancer patient; enhancing and expanding the data set by adopting a data enhancement technology, and adjusting and processing the image data; the method comprises the following steps: constructing a model, integrating a PEMA module at multiple positions of the model, introducing an EUCB up-sampling module into a decoder part, replacing standard convolution of the decoder part with lightweight dynamic convolution, and using a composite loss function MediBoundFusion Loss; the preprocessed training data set is input into the improved TransUNet network model to be trained; and the colorectal cancer focus is segmented by adopting the improved TransUNet network model after training is completed. The key problems that focus features are fuzzy, boundaries are difficult to define, forms are irregular, and effective features are difficult to extract due to low contrast of early cancerous tissues can be solved.

The invention belongs to the technical field of medical image detection, and particularly relates to an esophageal flora image intelligent detection method for risk prediction of gastroesophageal reflux disease, which comprises the following steps: acquiring flora images and clinical data, and constructing a perception network; quantifying flora displacement characteristics by using image registration; the method comprises the following steps of: extracting flora density, aggregation degree and fluorescence gradient characteristics by combining improved U-Net + + segmentation, fusing flora and epithelial cell lesion characteristics through space-time attention, generating a flora-host association map, constructing a flora dynamic evolution model by utilizing a space-time map convolutional network, predicting Barrett esophageal occurrence probability and flora diffusion trend, and predicting the occurrence probability of the Barrett esophagus. Calculating a lesion risk level through a flora imbalance quantification algorithm; in combination with reflux frequency and pH fluctuation, a flora-environment interaction model is used for simulating a field planting coefficient and correcting parameters, the parameters are transmitted to a diagnosis platform to deduce canceration risks, grading suggestions are triggered, and a visual report is generated. Therefore, the problems of long detection period, weak microscopic analysis capability and the like in the prior art are solved.

Treatment of damaged, diseased, abnormal, obstructive, cancerous or undesired tissue (e.g. a tumor, a benign tumor, a malignant tumor, a cyst, or an area of diseased tissue, etc) is provided by delivering specialized pulsed electric field (PEF) energy to target tissue areas in a specific dose so as to obtain a superior outcome. The PEF energy and delivery has been optimized to provide advanced treatment of target tissue areas, including destruction of undesired tissue and generation of improved inflammatory and immune responses. These various types of treatment are controlled by a variety of factors including the electrode geometry, the dose of PEF energy delivered, the time the energy is delivered over, and the waveform of the PEF energy itself. The PEF energy is delivered in the form a dose which is considered to be one application of the specialized energy. Each dose creates a lesion in the target tissue area.

The present invention relates to a multi-modal colorectal cancer pre-diagnosis information processing method, system, medium, and device. By converting image information into first-modal features, first clinical information into second-modal features, and family history information into third-modal features, and then performing feature fusion and inputting it into a neural network model of deep learning. Finally, the first pre-diagnosis report output can provide information on the disease risk level, stage feature prediction, canceration probability, and treatment plan of the current user. The multi-modal technology is applied to integrate various information sources such as the patient's personal information, image information, first clinical symptoms, and family history information, improving the comprehensive analysis of the colorectal diseases of the current user, enabling doctors to obtain a more comprehensive disease assessment, and thus achieving a more accurate risk level classification, disease stage prediction, and personalized treatment plan formulation, improving the efficiency and accuracy of the diagnosis and treatment process.

The invention discloses a resonant QCM biosensor-based CREPT protein quantitative detection device and method, a circular recessed area is constructed on a base, a silica gel circular ring is embedded at the bottom of the recessed area of the base, and a resonant QCM biosensor is arranged on the silica gel circular ring. On the basis, a hollow cylinder is placed on the base, and the circular through hole is matched with the circular sunken area, so that the high-sensitivity resonant QCM biosensor can be used for quantitatively detecting the CREPT protein. During quantitative detection, firstly, a pressure-frequency sensitivity coefficient KPf and a pressure-frequency coefficient CPf are calibrated, then an obtained HA-3HA tag protein liquid and an obtained HA-3HA-CREPT protein liquid are added to the surface of an upper electrode of a QCM biosensor respectively, and after the surface of the upper electrode is completely covered, according to the resonant frequency variation difference and the adding amount, the HA-3HA tag protein liquid and the HA-3HA-CREPT protein liquid are detected according to the resonant frequency variation difference and the adding amount of the HA-3HA tag protein liquid and the HA-3HA-CREPT protein liquid. And calculating to obtain the content of the CREPT protein. Therefore, low-cost and real-time on-line quantitative detection of early tumor cell biomarker-tumor cell regulation and evaluation protein is realized, and quantitative detection of early tumor canceration degree is further realized.

The invention belongs to the technical field of biological medicine, and discloses a cancer risk prediction and personalized vaccine preparation system and method based on single sample DNA sequencing, and the system comprises: a, a microsampling module; b, a multi-omics analysis engine; the engine synchronously executes the following operations: identifying a cfDNA terminal motif mode through a convolutional neural network; the presentation probability of the HLA-II type molecules is predicted on the basis of a Transform architecture; quantifying tumor mutation load (TMB) and microsatellite instability (MSI); c, a vaccine synthesis device; the device comprises: a programmable microfluidic mRNA synthesis chip; a self-assembly unit of lipid nanoparticles (LNP); and d, a closed-loop feedback system: monitoring the IFN-gamma through a wearable device to dynamically adjust the vaccine dosage. According to the invention, the early canceration detection rate can be improved, the antigen prediction accuracy is improved, the timeliness demand of early cancer intervention is met, and the adverse reaction rate is reduced.

The invention discloses an endometrial cancer diagnosis method based on a multi-mode flexible classification network, and the method comprises the steps: firstly, employing a knowledge distillation strategy, processing MRI images including a high-quality mode and an inferior mode through a student sub-network and a teacher sub-network, and enhancing the applicability and robustness of a model; secondly, a cross-modal feature enhancement module and a hierarchical fusion strategy are utilized to fully explore heterogeneity features and complementarity information among different modals, and the extraction capability and classification performance of a network model on key pathological features are enhanced; then, a flexible classification network structure is adopted to carry out self-adaptive weight adjustment and enhanced fusion on the multi-scale features of the multi-modal MRI image, and the diagnosis advantages of the multi-modal MRI image on endometrial cancer are exerted to the maximum extent; on the basis, a deep neural network is utilized to classify and diagnose canceration areas of the endometrium. Experimental results verify the effectiveness of the method.

The invention relates to the technical field of novel biological nanomaterials, in particular to a lung-targeted exosome complex as well as a preparation method and application thereof. The lung targeting type exosome complex is prepared from an NK cell exosome, lipid nanoparticles and an entrapped anti-tumor nucleic acid drug, the NK cell exosome is obtained by extracting a natural killer cell NK-92MI of a human malignant non-Hodgkin lymphoma patient through a differential centrifugation method. The anti-tumor nucleic acid drug is a specific nucleic acid drug targeting a key canceration driving gene in non-small cell lung cancer. The lung targeting type exosome complex prepared by the invention is an excellent and stable drug delivery carrier, has a good lung tissue targeting function, enhances the tumor targeting effect of the exosome, also exerts the tumor cell killing function of the exosome, and has important significance for the treatment of non-small cell lung cancer.

The invention relates to the technical field of bioinformatics, in particular to an esophageal cancer RNA-protein interaction space prediction method and device based on a graph neural network, and can solve the problem that it is difficult to accurately distinguish the difference of cancer tissue and normal tissue on RPI in a traditional method to a certain extent. The method comprises the steps of obtaining multi-stage space transcriptome data related to esophageal cancer, and performing preprocessing to obtain a multi-modal feature tensor and a canceration stage tag; using the multi-modal feature tensor and the canceration stage tag, using RNA and protein as nodes, defining a static edge based on sequence complementarity and structure matching degree, defining a dynamic edge based on spatial co-expression correlation, and constructing a space-time dynamic graph updated along with the canceration stage; the space-time dynamic graph serves as input, interaction existence, site coordinates and binding energy are predicted through space-time double-branch coding and attention mechanism fusion features, and an interaction prediction result is output.

Described herein are methods such as multi-omic methods for assessing a disease such as cancer. The multi-omic methods may integrate proteomic, transcriptomic, genomic, lipidomic, or metabolomic data. The method screening diseases or disease states. Also described herein are methods for screening for diseases or disease states from biological samples. The methods may include assessing whether a nodule, mass, or cyst is cancerous.

The invention discloses a fluorescent / photoacoustic dual-mode diagnosis and treatment probe for detection and photodynamic removal of senescent cells, a preparation method and application, the probe takes a sulfur-substituted hemicyanine dye as a parent structure, a novel bromo-glycoside ligand is covalently coupled, and a blue-green solid is obtained after gradient purification. The probe system shows a remarkable optical response characteristic on beta-galactosidase (beta-Gal) and ideal singlet oxygen (1O2) generation efficiency; an optical signal and a photodynamic therapy effect of the probe can be specifically activated by beta-galactosidase (beta-Gal) overexpressed in cancerous cells and senescent cells under a light excitation condition; the result is successfully verified in a palbociclib-induced senescence melanoma model. According to the probe disclosed by the invention, collaborative regulation and control of dual-mode visual monitoring and precise photodynamic therapy of beta-Gal enzyme activity are realized for the first time, a novel tool is provided for researching a molecular mechanism of cell aging and developing a diagnosis and treatment strategy of aging-related diseases, and the probe has a remarkable application value in the fields of anti-tumor treatment and degenerative diseases.

The invention belongs to the technical field of medical image processing, and discloses an OCT-SERS combined multi-mode gastric cancer tissue diagnosis system and method. A set of OCT-SERS combined system light path which shares a sample arm and is high in registration precision realizes high-precision registration of an OCT imaging range and an SERS detection position; the surface of a biological tissue is covered with a hydrogel film doped with silver nanoparticles, then SERS signal detection is carried out, and non-destructive SERS enhancement of the tissue is achieved; multi-modal gastric cancer diagnosis is carried out by adopting an artificial intelligence algorithm through collection of normal and cancerous gastric wall tissue OCT images and SERS spectral data and establishment of a database. According to the invention, by establishing the normal and cancer tissue OCT image and SERS spectrum database and carrying out artificial intelligence learning, real-time accurate diagnosis of pathological tissues can be realized.

The invention discloses a method for extracting calreticulin from tissues and application. The tissue cell extract extracted by the method contains calreticulin and can be used for preparing drugs or vaccines for preventing cancers. Experimental results show that after the tissue cell extract is immunized for several weeks, specific immune response of an organism can be triggered, cancerous cells in the organism can be removed, and therefore the aim of preventing cancers is achieved. The tissue cell extract provided by the invention can be used as a tumor preventive vaccine for preventing autologous or allogenic tumors and reducing the incidence rate of cancers in healthy people.

The present invention discloses a nucleic acid composition, a kit and a detection method for detecting methylation of liver cancer-related genes. The nucleic acid composition is a first nucleic acid composition, a second nucleic acid composition or a combination of the first nucleic acid composition and the second nucleic acid composition. The first nucleic acid composition comprises: a methylation-specific primer and a probe for a target site of the EMX1 gene, a methylation-specific primer and a probe for a target site of the OTX2 gene, and a methylation-specific primer and probe for a target site of the DAB2IP gene. The second nucleic acid composition comprises: a methylation-specific primer and a probe for a target site of the Septin9 gene, a methylation-specific primer and a probe for a target site of the CDKL2 gene, and a methylation-specific primer and probe for a target site of the GSTP1 gene. The kit configured with the nucleic acid composition discovered in the present invention determines whether a test sample has become cancerous based on the degree of DNA methylation of the test sample, thereby providing a clinically simple and accurate liver cancer screening method, which has a very positive significance for the detection of liver cancer.

This disclosure describes how to treat and / or improve pancreatic cancer using a novel proteomic profile of the pancreatic cancer. In some embodiments, the treatment includes removing cancerous tissue after taking a biopsy from the patient. Optionally, the treatment includes administering anticancer agents to suppress the progression of pancreatic cancer. In further or alternative embodiments, the novel proteomic profile is used to monitor disease progression or remission.

The application discloses a liver-targeted gene editing system based on endogenous promoter hijacking and application, and belongs to the field of biological medicine. The system is composed of an LNP-wrapped modified Cas nuclease mRNA (first component) and a promoter-free viral vector carrying a therapeutic transgene donor (second component). The system uses LNP to realize the transient burst expression of Cas nuclease in the liver, mediates the generation of double-strand breaks at the site of endogenous high-expression genes, induces the site-specific integration of therapeutic transgenes without exogenous promoters, and hijacks the expression driven by endogenous promoters by using the splice acceptor (SA) mechanism. The application solves the risk of carcinogenesis caused by random integration of exogenous strong promoters and the immunotoxicity of long-term expression of nucleases through a "double safety lock" design. Experimental results prove that the system has high editing efficiency, long-term stability and no off-target, and can be used for various liver-derived metabolic diseases such as hemophilia, hypercholesterolemia and the like.

The invention belongs to the technical field of medical biological detection, and particularly relates to a gene marker combination for oral mucosa leukoplakia canceration risk and application of the gene marker combination. The gene marker combination is a combination of TP53, CASP8 and CYP2B6 genes and is obtained by screening through a WES technology, the predicted AUC of the gene marker combination reaches 0.813 (95% CI: 0.710-0.916), and the performance of the gene marker combination is remarkably superior to that of traditional pathological grading. Through Cox risk regression analysis, a high-risk group as an independent factor has significant statistical significance and is superior to traditional indexes such as age and diseased regions. The invention further provides an oral mucosa leukoplakia canceration risk prediction kit and prediction system derived from the gene combination.

The present invention discloses a reagent kit and method for detecting bladder cancer. The reagent kit includes a DHFR PCR reaction mixture, Twist1 and TSC21 PCR reaction mixtures, a point mutation positive control, a methylation positive control, and a negative control. The present invention detects point mutations in the DHFR gene and the methylation levels in the promoter regions of the TSC21 and Twist1 genes in a sample, thereby achieving combined detection of gene point mutations and methylation and determining whether or not a sample has become cancerous. The present invention is easy to operate, simple to use, has high detection sensitivity, and good specificity, and is therefore of great significance in the detection of bladder cancer.

Systems and methods for identifying a diagnosis of a cancerous state for a somatic tumor specimen of a subject are provided.SOLUTION: The method receives sequencing information comprising an analysis of a plurality of nucleic acids from a somatic tumor specimen. The method identifies a plurality of features from the sequencing information including two or more of RNA, DNA, RNA splicing, viral, and copy number features. The method provides a first subset of features and a second subset of features from the identified plurality of features as input to a first classifier and a second classifier, respectively. The method generates two or more predictions of cancer status based at least in part on the identified plurality of features from the two or more classifiers. The method combines the two or more predictions with a final classifier to identify a diagnosis of cancer status for the subject's somatic tumor specimen.SELECTED DRAWING: Figure 1

The invention belongs to the technical field of biological medicines, and particularly relates to application of CDK9 as a target spot in preparation of a medicine for preventing and treating oral leukoplakia canceration. The invention proves that the phenomenon of transcriptional activity increase and the characteristic of transcription addiction exist in the oral leukoplakia canceration process, and a driving factor cyclin-dependent kinase 9 (CDK9) closely related to oral leukoplakia transcriptional disorder is screened out. Moreover, a molecular mechanism of CDK9 driving oral leukoplakia transcription addiction is further clarified, an important role of CDK9 in an oral leukoplakia canceration process is clarified, and transcription addiction of oral leukoplakia cells can be effectively inhibited through targeted intervention of activity or expression level of CDK9, so that canceration potential of oral leukoplakia can be effectively prevented and treated.

The invention discloses an oral leukoplakia canceration progress recognition method based on deep learning. The method comprises the steps of performing preprocessing of unified size zooming, pixel normalization and data enhancement on oral clinical photos; constructing a three-classification network architecture composed of a ConvNeXt backbone network, a dynamic feature refining module and a classification head, wherein the feature refining module realizes feature optimization through a learnable clustering center and a transformation matrix; performing model training by adopting a two-stage fine tuning strategy, fixing backbone network parameters in the first stage and only updating refining module and head parameters, and jointly optimizing all parameters in the second stage; and inputting the preprocessed to-be-diagnosed image into the trained network, and outputting a normal / white spot / white spot canceration classification result and a confidence score. According to the method, three-level intelligent evaluation of oral lesions of normal-precancerous-cancerous is realized for the first time, the classification accuracy of the test set reaches 90% or above, and the method has the characteristics of high clinical applicability and high reasoning efficiency.

The invention relates to the technical field of colorectal cancer auxiliary detection, and particularly discloses a blood methylation site combination and a detection kit for early diagnosis of colorectal cancer, and the method comprises the following steps: providing a blood sample of a person to be detected for obtaining cfDNA; the cfDNA is subjected to bisulfite treatment, and the transformed DNA is obtained; amplifying the transformed DNA by using a multiplex fluorescence PCR (Polymerase Chain Reaction) method to obtain fluorescence signal data of each gene; calculating a Ct value of each gene based on the fluorescence signal data, comparing the Ct value with a preset Cut-off value, and judging whether the colorectal cancer exists or not; according to the present invention, the invasive operation of the colonoscope can be replaced, the screening can be completed through the blood sample, the patient compliance can be significantly improved, the method is suitable for the large-scale early screening, the trace tumor signal in the blood can be efficiently captured based on the methylation marker highly related to the colorectal cancer, and the accurate early canceration identification can be achieved.

Method and device to treat cancer after surgery in the gastrointestinal tract. The device can be used in a method comprising of removing cancerous cells from a cancerous site on a tissue or organ of a patient, positioning a biodegradable device having a cancer treatment agent to cover the cancerous site, securing the biodegradable device to the cancerous site such that an outer wall of the device extends across the cancerous site, and leaving the biodegradable device at the cancerous site for treatment of microcells left adjacent to the cancerous site.

The application relates to a method for predicting gene mutation based on deep learning using multi-modal slices, image block division is performed on a digestive tract HE slice, and based on the image block division result, each image block of the digestive tract HE slice is classified into a cancerous region; the digestive tract HE slice and an immunohistochemical slice are registered; based on the digestive tract HE slice and the registered immunohistochemical slice, a gene mutation prediction training sample set is constructed, a multi-instance learning model is trained, the training standard is whether a gene is mutated, and a gene mutation prediction model is obtained; gene mutation prediction is performed according to the obtained gene mutation prediction model, a model for predicting gene mutation in combination with multi-modal pathological data of a patient is used, high specificity of the model is ensured, compared with a pathological gene prediction model using single modal data, more modal data is introduced, and the prediction accuracy is effectively improved.

The present disclosure provides compositions and methods for distinguishing between non-cancerous, pre-cancerous, and cancerous conditions in the esophagus. In particular, the present disclosure provides compositions and methods for distinguishing non-dysplastic Barrett's esophagus (NDBE) samples from pre-cancerous (e.g., low-grade or high-grade dysplasia) and / or cancerous (e.g., esophageal adenocarcinoma) samples based on methylation status and / or DNA copy number abnormalities.

The present invention belongs to the field of molecular biology detection, specifically, to the field of lung cancer detection, and more specifically, to the detection of methylation levels of lung cancer gene markers. The present invention provides a methylation marker combination for auxiliary detection of lung cancer, comprising: a region in the AHDC1 gene as shown in SEQ ID NO: 1. The sensitivity, specificity and AUC of lung cancer detection using the markers of the present invention are 88.49%, 91.43% and 0.936, respectively. The present invention can detect lung cancer clinically with fewer markers, saving both cost and time, and can detect patients who are truly at risk of lung cancer malignancy in the early stages of the carcinogenesis process with high sensitivity and high specificity.

The invention provides a construction method and application of an endometrial cancer CT image segmentation model. The construction method comprises the following steps: acquiring a plurality of endometrial CT images marked with canceration regions as a training data set; constructing an endometrial cancer CT image segmentation framework, wherein the endometrial cancer CT image segmentation framework is of a U-Net structure comprising a coding unit, a bottleneck layer and a decoding unit; and training the endometrial cancer CT image segmentation architecture by using the training data set to obtain an endometrial cancer CT image segmentation model. According to the scheme, multi-scale structure change information is explicitly captured by constructing a multi-direction coding structure response operator and generating a coding structure gradient field, and representation of thin and weak boundaries and small lesions is enhanced to improve the segmentation accuracy of the model.

The invention relates to the field of intelligent medical treatment, in particular to an oral mucosa canceration prediction method and device based on a pathological image and a program product. Comprising the following steps: S1, acquiring a pathological image of oral mucosa tissue of a to-be-detected person; s2, phenotypes of microvessels are obtained based on the pathological image, the phenotypes comprise an elliptic type and a non-elliptic type, when the phenotype is the non-elliptic type, ANGPTL2 gene detection is carried out to obtain a gene expression quantity, and when the gene expression quantity of ANGPTL2 is larger than a first preset threshold value, it is judged that a prediction result of oral mucosa canceration occurs, and if the prediction result of oral mucosa canceration occurs, the prediction result of oral mucosa canceration does not occur. The method can be used for oral mucosa canceration prediction and progress prediction, and has a very good clinical value.

The present invention relates to a monomer self-assembled and polymerized by thioesterase and reactive oxygen species in cancer cells and a use thereof. According to the present invention, the monomer represented by chemical formula 1 is selectively accumulated in mitochondria and undergoes the deprotection of the acetyl protecting group from the thioacetyl group by thioesterase within cancerous cells to expose a thiol group which is then activated by reactive oxygen species (ROS) within cancerous cells to form disulfide bonds, leading to self-assembly polymerization into a macromolecular polymer that selectively disrupts cancerous mitochondria. In normal cells, deprotection of the acetyl group does not occur, so the monomer remains as it is, exerting no effect.

The invention relates to the technical field of near-field imaging, in particular to a papillary thyroid carcinoma identification method based on terahertz imaging. According to the technical scheme, the method comprises the following steps that two sets of sections at the same position of the thyroid tissue of a patient are obtained, one set is stained sections, and the other set is unstained sections; and comparing the two groups of slices through an optical microscope, observing the position corresponding relation of the two groups of slices, and selecting an observation area based on cell morphological characteristics. According to the invention, synchronous acquisition of tissue apparent morphology and internal structure under nanoscale resolution is realized through the terahertz near-field imaging system, automatic analysis of an undyed thyroid section can be completed within 30 minutes by combining multi-modal feature fusion and a target detection algorithm, objective positioning and diagnosis scores of a cancerous region are directly output, and the accuracy and accuracy of diagnosis of the cancerous region are improved. And rapid, lossless and quantitative papillary thyroid carcinoma identification is realized.