94 results about "Tumor type" patented technology

The invention relates to the technical field of tumor data processing, in particular to a methylation-based tumor data processing system. The system comprises the following modules: a methylated sample sequencing module, a sequencing difference site recognition module, a tumor gene sequence analysis module and a tumor subtype classification module, performing high-throughput sequencing on the to-be-detected clinical tumor DNA sample to obtain methylated tumor sequencing data; performing methylation level quantification on the methylated tumor sequencing data, and performing tumor difference site analysis to generate tumor difference site data; performing tumor generation key gene sequence identification according to the tumor difference site data to generate tumor methylation characteristic data; and performing tumor subtype tag identification according to the tumor methylation characteristic data to generate tumor type tag data. According to the method, accurate tumor typing is realized on the basis of tumor DNA methylation characteristic analysis, and the false negative rate of low-concentration sample detection is effectively reduced.

The invention discloses a method and a system for constructing an intestinal obstruction pathogenesis identification model based on multi-phase feature fusion, which are suitable for clinical diagnosis scenes with complex intestinal obstruction types and various image expressions. The method comprises the following steps: acquiring a multi-stage CT image of a patient, performing image preprocessing and structural partitioning, extracting phase-to-phase structural consistency, identifying a pseudo-difference area and a non-focus interference area, and suppressing the characteristics of the pseudo-difference area and the non-focus interference area; and meanwhile, in combination with disease cause region difference enhancement, structure expectation template comparison and dynamic tolerance analysis, intelligent discrimination of multiple disease causes such as adhesion type, tumor type, telescoping type and the like is realized. The system has the advantages of being high in model interpretability, sensitive to negative signs and high in artifact interference resistance, and the accuracy and clinical applicability of automatic identification of ileus causes are improved.

The invention relates to the field of medical resource scheduling, in particular to a multi-chamber particle therapy method, system and device, a storage medium and a computer storage medium, and the system comprises an irradiation source which is used for generating a particle beam; the plurality of particle treatment rooms are used for sending beam requests and receiving the particle beams; the beam transport device is used for transmitting the particle beam from the irradiation source to the particle treatment room; and the control device is used for receiving the beam requests of the particle treatment room, calculating the priority for each beam request according to the reserved irradiation time, the tumor type and the patient condition included in each beam request, and controlling the beam transport device to transport the particle beams according to the priorities. According to the method, the utilization efficiency of beam resources can be remarkably improved, the urgency degree and clinical importance of treatment are fully considered, and the demand intensity of different requests for the beam resources can be quantitatively reflected.

The invention relates to the field of medical artificial intelligence, in particular to a mucus-like brain tumor multi-source data auxiliary differential diagnosis system based on deep learning, and the system collects pathological images, medical images, immunohistochemical data and molecular biology data through a multi-source heterogeneous data collection and standardization module, and carries out standardization processing; a multi-scale feature extraction module extracts key features from the data to generate multi-modal feature data; a cross-modal correlation analysis module analyzes correlation among the feature data and generates attention mapping data and feature correlation data; the diagnosis reasoning and decision-making module identifies the tumor type by using the data, carries out differential diagnosis and calculates the uncertainty of a diagnosis result; the interpretability display module is used for generating a structured diagnosis report which comprises multi-level attention visualization data and positioning a key diagnosis area; and through multi-source data fusion and correlation analysis, the diagnosis accuracy is remarkably improved.

The present invention provides the use of an agent targeting the interaction between STC2 and Cav1.2 in the preparation of a drug for tumor prevention, treatment, or drug resistance enhancement. The agent targeting the interaction between STC2 and Cav1.2 is selected from an agent that inhibits STC2 expression, an agent that promotes Cav1.2 expression, or a combination of the two. The interaction between STC2 and Cav1.2 discovered in the present invention can be used for targeted therapy of ovarian cancer or other tumor types.

A system for generating a cancer alleviation nourishment plan including a computing device configured to receive at least a cancer biomarker relating to a user, where the cancer biomarker indicates the presence of cancer, retrieve a cancer profile related to the user, assign the cancer profile to a cancer category, wherein the cancer category includes a determination of a type of tumor, identify, using the cancer profile, a plurality of nutrition elements for the user, identifying, as a function of the plurality of nutrient amounts, the plurality of nutrition elements for cancer alleviation, and generate, using the plurality of nutrition elements, a cancer alleviation nourishment plan. A method for generating a cancer alleviation nourishment plan is also disclosed.

A method for controlling ultrasonic waves to induced sonoporation of a drug into cancer cells in a tumor. The method may include accessing configuration data that may include a type of the tumor and a type of drug, and determining values of operational parameters that may be based on the configuration data to define determined values. The operational parameters may include frequency value and duty cycle value. The method may also include determining frequency value which may be based on the type of tumor that may define a determined frequency value, and determining the duty cycle value which may be based on the type of drug and the type of tumor that may define a determined duty cycle value.

This platform is a privacy-preserving, federated learning system designed to integrate whole-slide digital pathology images with matched molecular profiling and clinical metadata for improved diagnosis, subtyping, and prognostic estimation of gynecologic tumors. The architecture comprises local institutional nodes that retain raw patient data while participating in distributed model training coordinated by a central orchestration server. Each local node preprocesses whole-slide images into patch-level tensors, extracts visual embeddings via convolutional backbones, and processes molecular vectors (e.g., somatic mutations, expression summaries, copy-number measures) via a molecular encoder. A multimodal fusion module - implemented as an attention- based transformer - integrates image and molecular embeddings into a unified representation used by multi-task heads for classification (histologic subtype, diagnostic label) and regression (risk score). The federated learning controller aggregates encrypted model updates (FedAvg) and returns improved global weights without exchanging raw data, enabling cross-site generalization while preserving patient privacy. Explainability components generate attention maps and tile-level saliency (Grad-CAM style) linked to molecular features, providing interpretable morpho- molecular correlations to pathologists. The platform supports API integration with PACS / LIMS, conforms to privacy standards via optional differential privacy and secure aggregation layers, and is extensible to additional omics modalities or transfer / fine-tuning workflows for related tumor types. By combining multimodal fusion, federated training, and clinician-facing interpretability, the system accelerates robust, generalizable AI for precision pathology in gynecologic oncology.

The invention belongs to the technical field of tumor immunity, and particularly relates to a tumor antigen and chemotactic factor co-coding system and application thereof. The invention provides a tumor antigen and chemotactic factor co-coding system. The tumor antigen and chemotactic factor co-coding system comprises a nucleotide sequence for coding a tumor antigen and a nucleotide sequence for coding a chemotactic factor. The tumor antigen and chemotactic factor co-coding system can flexibly replace an antigen sequence and chemotactic factor combination, is adaptive to different tumor types and various immunotherapy requirements, can be expanded to various solid tumor treatment scenes through a customized antigen-chemotactic factor combination in the future, and has a wide application prospect. The broad-spectrum application in tumor treatment means including tumor neoantigen vaccines, adoptive cell therapy and the like is realized.

The present invention relates to the field of pathology analysis technology, and more specifically to a tumor pathology analysis method based on multimodal artificial intelligence, comprising the following steps: acquiring multi-center, multi-type whole-slice tissue images, cutting the whole-slice images into pathology images, and dividing the standardized pre-processed pathology images into training and test sets; constructing a contrastive language and image model for capturing key features in pathology images through a two-stage pre-training process; and fine-tuning the model using the pre-trained weights of the contrastive language and image model as initial weights and adding task-specific fully connected layers to obtain a pathology analysis model for implementing different classification and regression tasks in tumor pathology analysis. By integrating multimodal information from images and text, the present invention can more comprehensively assess tumor type, stage, and prognosis, thereby fully leveraging the advantages of multi-source data and effectively addressing the current bottlenecks in tumor pathology analysis technology.

The invention discloses a tumor tissue segmentation method based on an MR image, and relates to the technical field of image processing, and the method comprises the following steps: processing before segmentation, obtaining the MR image, quantifying texture features, calculating different-dimension feature values of each pixel of the MR image, obtaining a multi-scale texture feature vector of each pixel, and classifying the texture features. The method comprises the steps of dividing a pixel category and an image area of each pixel, enhancing boundary dynamic features and adjusting a threshold value, and has the advantages that double-weight boundary filtering is carried out by adopting confidence and spatial distance, similar texture features in a boundary transition area are amplified, boundary over-segmentation and under-segmentation probabilities are reduced, the judgment accuracy of the pixels in the boundary transition area is improved, and the judgment accuracy of the pixels in the boundary transition area is improved. According to the method, the threshold value of each image can be dynamically adjusted according to the tumor features of the image, manual parameter adjustment is not needed, multi-scene adaptation is achieved, the efficiency is improved, and through combination of multi-scale textures and dynamic double-feature fusion, the segmentation precision of cross-tumor types is guaranteed, and the heterogeneity tumor adaptability is improved.

The invention belongs to the field of medicinal chemistry, and particularly relates to a targeted drug coordinated metal complex as well as a preparation method and application thereof. The metal complex prepared by the invention is a ruthenium (II), iridium (III) and rhodium (III) complex coordinated with a targeted drug, the original biological activity of the ligand is remarkably optimized and improved by virtue of the synergistic effect between central metal ions and the ligand, the specific binding capacity of the ligand with a tumor cell target spot is enhanced, and the tumor cell target spot is further enhanced. The metal complex has a broad-spectrum and efficient anti-tumor activity, the action range of the metal complex can cover multiple common tumor types including but not limited to liver cancer, kidney cancer, breast cancer, ovarian cancer or colorectal cancer and the like, and an important technical support is provided for developing novel anti-tumor drugs with multiple target points and low toxic and side effects. The complex provided by the invention is novel in structure and good in anti-tumor activity, and has a good application prospect in the field of anti-tumor drugs.

The application discloses application of a pharmaceutical composition taking GL-V9 and a chemotherapeutic drug as active ingredients in treatment of tumors. When GL-V9 is combined with a classical chemotherapeutic drug to treat tumors, a drug synergistic effect can be obviously achieved, and the effect is obviously superior to combination of similar drugs and the chemotherapeutic drug. The chemotherapeutic drugs include 5-fluorouracil; and the tumor types include leukemia, colorectal cancer and lung cancer.

This invention discloses an intelligent nutrition recommendation method for cancer patients based on metabolic rhythm synchronization, belonging to the field of nutrition recommendation. This invention integrates temporal physiological data and clinical information, extracts features, and uses a bidirectional long short-term memory network to predict the host metabolic activity curve. Based on a tumor knowledge graph, a conditional generative adversarial network is constructed to infer and generate a tumor metabolic activity curve using the host curve, tumor type, and treatment stage as conditions. A temporal separation potential heatmap is generated by calculating the phase difference and overlap between the two curves. Using the heatmap and clinical labels as states, an integrated constraint proximal strategy optimization algorithm is used for decision-making, outputting a time-segmented nutrient delivery action sequence that satisfies temporal nutritional constraints. Using this sequence as the target, an optimization algorithm performs a multi-objective search on a recipe database to generate a personalized daily recipe that considers both nutritional and taste preferences, providing cancer patients with timely and intelligent decision-making.

This invention discloses an antibody-drug conjugate based on a p16-targeting single-chain antibody, comprising a p16 single-chain antibody, a cell-penetrating peptide, a linker, and a carrier drug. The p16 single-chain antibody and the cell-penetrating peptide are fused together to form a fusion protein, which is further conjugated to the carrier drug via a linker to form the antibody-drug conjugate. This invention provides a novel therapeutic strategy by targeting p16, particularly suitable for tumor types that highly express p16, for which effective treatments are currently lacking. By targeting the p16 site within the cell nucleus, this invention not only enriches the candidate target library for targeted therapy but also provides feasibility validation and technical reference for future drug development targeting nuclear targets.

The invention relates to a multi-modal ultrasonic image-based knowledge graph construction method and device, and a storage medium, and the method comprises the steps: obtaining a tumor gray-scale ultrasonic image, obtaining a tumor edge image and a tumor internal image through target segmentation, respectively extracting corresponding multi-modal candidate image omics features, and carrying out the target segmentation; forming a sample set comprising a plurality of samples in combination with a tumor type corresponding to the tumor gray-scale ultrasonic image; performing synthetic minority oversampling processing on a sample set, performing Z scoring processing on each candidate radiomics feature in each sample, screening radiomics features with strong correlation through principal component analysis, and performing recursive feature elimination to obtain finally reserved radiomics features corresponding to each tumor type; and establishing a knowledge graph and / or a machine learning model based on the finally reserved radiomics features corresponding to each tumor type. The method has the advantages that the association between the tumor type and the selected iconography features is fully established, and the abundant information of the tumor edge is fully considered.

The invention discloses a drug action analysis method and device based on homogeneity of tumor organoids, and relates to the technical field of tumor organoids. According to the method, after the original three-dimensional structure data of the tumor type organ is obtained, the connected domain data corresponding to each type organ in the target type organ cluster is determined, so that the spherical coordinate system is established by taking the centroid of each type organ as an original point, and according to the polar radiuses corresponding to the type organ entities with different polar angles and different azimuth angles, the three-dimensional structure data of the tumor type organ is obtained. And determining the morphological homogeneity of each organ, carrying out point multiplication on the connected domain data of each organ and the original three-dimensional structure data to obtain the intensity information of each organ, and analyzing the intensity homogeneity of each organ. Therefore, the tumor heterogeneity is reflected by the form homogeneity and the strength homogeneity of each organoid, and on the basis, the tumor organoid is classified to construct the growth level model of the tumor organoid for drug action analysis, so that the classification accuracy of the tumor organoid is improved, and more targeted research on the tumor organoid is realized.

Methods for enriching disseminated tumor cells (DTCs) or circulating tumor cells (CTCs) from a biological sample are provided. Methods for identifying disseminated tumor cells (DTCs) or circulating tumor cells (CTCs) or identifying a tumor type or tissue of origin of a tumor are also provided. Methods of identifying a druggable cancer target and a cancer drug against the target are provided.

The application belongs to the technical field of tumor typing, and discloses a tumor gene typing prediction method and system based on a multi-modal data graph structure, which comprises the following steps: acquiring sample pathological images and sample multi-omics characteristics of tumor samples; inputting the pathological images into a Hyper-RBAT-Net network to output corresponding structured mask images, and constructing a three-level pathological structure atlas based on the mask images; jointly embedding the three-level pathological structure atlas and the sample multi-omics characteristics to construct a fusion graph structure, learning a graph representation of the fusion graph structure, and obtaining a sample embedding representation; using the sample embedding representation to predict tumor typing, defining a loss function, training a tumor typing prediction model, and using the trained model to predict tumor gene typing. The application can more comprehensively mine the structural expression information of tumors by constructing a three-level pathological structure atlas, fusing multi-omics characteristics, and using an improved graph attention mechanism to learn a graph representation, thereby improving the accuracy and generalization ability of gene typing.

A three-dimensional scaffold for use in engineered tissue includes a repeated 3D geometry; and at least one of a hydrogel, a biocompatible polymer, and a bioprintable polymer. The repeated 3D geometry may include an open geometry including a plurality of interconnected nodes configured to be seeded with living cells. The scaffold may be formed via bioprinting. The three-dimensional scaffold may also be used for (1) 3D tissue modelling (for liver, kidney, gut, pancreas, heart, lung, spleen, etc.), (2) disease modeling of different tumor types such as breast, colorectal, lung, liver, brain, ovarian and others, (3) drug testing / therapeutic screening of small molecule drugs, peptides, proteins, antibodies, ADCs, gene therapies, RNA-based therapeutics, cell therapies, and tissue therapies, and (4) therapeutic / drug delivery (i.e., via delivery device that can be used to control drug release based on different patterns).

IT-139, sodium trans-[tetrachlorobis(1H-indazole)ruthenate(III)], is an intravenously administered small molecule compound. In preclinical anti-tumor and mechanism of action studies, IT-139 showed activity against a broad range of tumor types, including those which are resistant to standard anti-cancer agents (e.g., platinums, vinca alkaloids, taxanes, anthracyclines). This activity is believed to arise from IT-139's novel mechanism of action that targets the GRP78 pathway. It was found that up-regulation of GRP78 is a key cancer cell survival pathway. Downregulation of GRP78 using IT-139 removes this resistance pathway allowing for chemotherapy and immuno-oncology agents to be more effective in treating cancer.

The application discloses a 3'-deoxyadenosine compound and application thereof in preparation of an antitumor drug. The 3'-deoxyadenosine compound and the pharmaceutical composition thereof have good antitumor proliferation effect. Compared with a parent drug, the 3'-deoxyadenosine compound has better affinity to a cell membrane, so that the half-life of in-vivo metabolism of the drug is longer, and the drug stays in the body for a longer time. Compared with other nucleoside antitumor drugs, the cordycepin derivative and the pharmaceutical composition thereof have a wider range of tumor types and effects, including excellent inhibition effect on gastric cancer, pancreatic cancer, liver cancer, small cell lung cancer, colorectal cancer, melanoma, ovarian cancer and the like, and the side effect is lower and the curative effect is better.

This disclosure describes a machine learning (ML) framework, including a graph convolutional neural network (GCN), for identifying gene expression signatures associated with cancer driver events. The model is trained to identify the TP53 mutation status of cancer samples from gene expression, utilizing a comprehensive, curated graph structure of gene interactions. Quantitative scores are generated to rank the severity of driver events in each sample. Very high AUC results for unknown data across several tumor types are achieved in this method. A strong correlation with protein function exists. The Signature in Transcriptome Associated with Mutant Proteins (STAMP) model can also predict driver events in many combinations of key oncogenes / pathways and several tumor types, based on well-established annotations from the literature. Thus, the STAMP model can identify and quantify driver events, which may lead to improved targeted therapy selection and prioritization in cancer patients.

The present invention relates to the use and detection system of markers for tracing the origin of tumor tissues of unknown primary lesions, and belongs to the field of tumor gene detection technology. This study used plasma cfDNA from 17 tumor types, including lung cancer, intestinal cancer, hepatobiliary cancer, gastric cancer, head and neck cancer, kidney cancer, breast cancer, pancreatic cancer, ovarian cancer, prostate cancer, thyroid cancer, cervical cancer, urothelial cancer, esophageal cancer, endometrial cancer, sarcoma, and melanoma, to study the differences in gene copy number variation in different tumor tissues, and screened out regions of gene copy number variation with significant differences. Then, using a method constructed by the H2O AutoML classifier, 140 optimal differential gene copy number variation regions were screened for the first time to establish a diagnostic prediction model for tracing the origin of tumor tissues of unknown primary lesions. The model is suitable for diagnosing and predicting the tissue tracing of tumors of unknown primary lesions, and is suitable for diagnosing the tissue origin of tumors of unknown primary lesions, and for diagnosing people with tumors of unknown primary lesions.

Systems, methods, and computer programs disclosed herein relate to training a machine learning model and using the trained machine learning model to classify images, preferably medical images, using multiple-instance learning techniques. The machine learning model can be trained, and the trained machine learning model can be used for various purposes, in particular for the detection, identification and / or characterization of tumor types and / or gene mutations in tissues.

This application relates to the field of intelligent medicine, and specifically relates to a method, device and program product for tumor methylation typing and discovery of new subtypes based on multi-task learning. It includes: S1, obtaining tumor methylation data; S2, inputting the tumor methylation data into a trained first neural network and a second neural network in parallel, where the first neural network performs feature processing to obtain feature data, and the second neural network performs classification to obtain a classification type; S3, inputting the feature data and the classification type into a trained third neural network to obtain a classification prediction value, and comparing the classification prediction value with a preset threshold. When the classification prediction value is less than the preset threshold interval, it is determined as a new subtype, otherwise it is determined as a known type. This application can detect new subtypes when obtaining the tumor type, and has good clinical value.

The present invention discloses a tsRNA molecule, tRF-28-Q99P9P9NH50E, and its applications. This novel molecule is associated with liver cancer. Next-generation sequencing and quantitative polymerase chain reaction (qPCR) validation confirm its upregulated expression in liver cancer. This tsRNA molecule has not been previously discovered in studies of liver cancer, other tumor types, or non-tumor conditions. The tRF-28-Q99P9P9NH50E inhibitor inhibits liver cancer cell proliferation, invasion, and migration, has profound clinical significance, and enhances the potential for liver cancer treatment.

The present invention relates to the preparation and application of aminoquinazoline compounds that dual-target EGFR and ACK1, and belongs to the technical field of anti-tumor pharmaceuticals. The technical problem addressed by the present invention is to provide a compound that acts as a dual-target EGFR and ACK1 inhibitor. The compound includes the compounds shown below, or pharmaceutically acceptable salts thereof. The compounds of the present invention, or pharmaceutically acceptable salts thereof, can act as inhibitors of EGFR and ACK1, exhibit anti-tumor activity, and can effectively inhibit the growth of tumor cells. The compounds of the present invention are preferably anti-tumor compounds targeted to tumor types characterized by overexpression of EGFR and ACK1.

A combination therapeutic strategy employs multiple oncolytic viruses (OVs), grouped and administered based on their virological properties, tumor selectivity, and distinct antigen profiles, to treat malignant tumors. Representative groupings may include members of flaviviruses, each contributing distinct immune modulation and the same modes of tumor cell killing. A predefined treatment schedule involves sequential or concurrent administration of antigenically diverse OVs in multiple cycles, reducing cross-neutralization and sustaining cytolytic pressure on tumors. A pre-characterized OV panel, comprising members from a virus family, RNA and DNA viruses, both wild-type and genetically engineered, serves as a flexible resource for customizing treatment regimens by tumor type, immune landscape, and therapeutic goals. This platform establishes a rational framework for combination OV therapy with improved durability, safety, and clinical effectiveness.

A method (100) for visualizing heterogeneity of a patient's tumor, comprising: (i) receiving (120) information about a patient, comprising demographic and clinical information about the patient, an identification of the patient's tumor type, and a heterogeneity assessment of the patient's tumor; (ii) obtaining (130), based on the identification of the patient's tumor type and the heterogeneity assessment of the patient's tumor, therapy effectiveness information for each of the two or more subclones of the tumor: (iii) generating (140) a visual representation of the heterogeneity assessment of the patient's tumor and the obtained therapy effectiveness information for each of the two or more subclones of the tumor; and (iv) providing (150), via a user interface of the system, the generated visual representation, wherein the visual representation comprises a tumor heterogeneity graph and a therapy effectiveness graph.