Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

24results about How to "High diagnostic value" patented technology

Medical visual question and answer method and system based on multi-task modeling

The invention discloses a medical visual question-answering method and system based on multi-task modeling, and the method comprises the steps: carrying out the feature extraction of a to-be-analyzed medical image through a visual encoder, obtaining an image feature, inputting a preliminary question instruction and historical question-answering data into a dialogue large model to generate a question instruction, and obtaining a text feature through a text encoder; carrying out feature fusion on the obtained text features and image features, and carrying out self-attention image importance weighting processing and image-text alignment to obtain image-text fusion representation; and inputting a multi-target output projection layer, carrying out multi-task prediction, outputting question answers, image categories and important region masks, inputting the question answers and the image categories into a dialogue large model, and finally generating diagnosis opinions with detailed description in combination with dialogue context and multi-round interaction data and in combination with the important region masks. According to the invention, the interaction experience and the performance of the question and answer system are improved, and more accurate medical diagnosis in multi-modal complex information is facilitated.
Owner:ZHEJIANG UNIV

Image three-dimensional post-processing method and system based on multiple modes

PendingCN119048694Ashow flexiblehigh diagnostic valueImage enhancementImage analysisTissue architectureData set
The invention provides an image three-dimensional post-processing method and system based on multiple modalities, and relates to the technical field of image processing.The method comprises the steps that CT image data, MRI image data and PET image data are obtained and preprocessed, and preprocessed data are obtained; performing feature extraction on the preprocessed data to obtain skeleton structure features, soft tissue structure features and metabolic activity features; performing rigid registration on the skeleton structure features and the soft tissue structure features to obtain preliminary registration data; performing elastic registration on the preliminary registration data set and the metabolic activity characteristics to obtain multi-modal image data; generating a three-dimensional reconstruction model according to the multi-modal image data; segmenting the three-dimensional reconstruction model to obtain lesion analysis data; analyzing according to the lesion analysis data to obtain lesion marking data; and performing dynamic weight fusion processing on the lesion mark data and the tissue structure data to obtain three-dimensional comprehensive image data. The invention provides a more accurate influence processing method.
Owner:FUJIAN ZHIKANGYUN MEDICAL TECH CO LTD

Method for accelerating high-quality MRI (Magnetic Resonance Imaging) image reconstruction based on TC-KANReccon model

The invention relates to an accelerated high-quality MRI (Magnetic Resonance Imaging) image reconstruction method based on a TC-KANReccon model. The method comprises the following steps: S1, collecting and preprocessing image data; s2, an accelerated high-quality MRI image reconstruction model based on a TC-KANReccon model is built; and S3, designing a noise cutting strategy of linear reduction of the cutting threshold. In each step of the sampling process, a linear decreasing cutting strategy is adopted according to the current progress of the sampling step. The strategy is applied to noise estimation generated by an MF-UKAN diffusion trunk so as to generate an MRI image with a better visual effect; s4, repeatedly training a diffusion model and a VAE module by taking the preprocessed MRI image and the full-sampling k-space data as input, optimizing network parameters, and continuously performing iterative optimization; and S5, inputting the under-sampled k-space data into the trained accelerated high-quality MRI image reconstruction model based on the TC-KANReccon model, and applying a matched noise cutting strategy of linear reduction of a cutting threshold to finally generate a high-quality MRI image.
Owner:HANGZHOU DIANZI UNIV

Application of protein in small extracellular vesicles as prostate cancer diagnostic marker

ActiveCN119125561AHigh AUC valueHigh specificity and sensitivityMaterial analysisAntigenPsa antigen
The invention discloses application of small extracellular endovesicular protein as a prostatic cancer diagnostic marker, and is characterized in that the small extracellular endovesicular protein is plasma sample sEV protein LAMB1 and / or urine sample sEV protein Histone H4, and the plasma sample sEV protein LAMB1 is applied as a metastatic prostatic cancer diagnostic marker. The sEV protein LAMB1 of the plasma sample is combined with a prostate specific antigen to serve as metastatic prostate cancer; the application of the sEV protein Histone H4 in the urine sample as a prostate cancer grading diagnosis marker, the application of the sEV protein Histone H4 in the urine sample as a high-risk prostate cancer diagnosis marker and the application of the combination of the sEV protein Histone H4 in the urine sample and a prostate specific antigen as the high-risk prostate cancer diagnosis marker have the advantages of high sensitivity and strong specificity.
Owner:NINGBO FIRST HOSPITAL

OCT (Optical Coherence Tomography) image processing method and system for adaptive weighted bilateral filtering deconvolution

The invention relates to an adaptive weighted bilateral filtering deconvolution OCT image processing method and system, and the method comprises the steps: carrying out the preprocessing of an original OCT signal, including background noise removal, wave number calibration, spectrum shaping and dispersion compensation, so as to obtain an OCT reconstructed image; enhancing the contrast ratio through histogram stretching, adjusting the space weight and the intensity weight of the OCT stretching image, and performing adaptive denoising on the image; and further optimizing the image by using a blind deconvolution algorithm, and iteratively updating the estimated image and a point spread function (PSF) to obtain a high-definition OCT reconstructed image. According to the method, efficient denoising and detail reservation of the OCT image are realized through adaptive weighted bilateral filtering and blind deconvolution technologies, so that a high-definition reconstructed image is obtained.
Owner:XIAMEN UNIV

Self-adaptive motion track intelligent image acquisition method

The invention relates to a self-adaptive motion trail intelligent image acquisition method, which comprises the following steps of: monitoring tiny physiological motion of a patient in imaging by utilizing an integrated Doppler radar sensor and an inertial measurement unit, and generating physiological motion data; extracting features of the data through a convolutional neural network for real-time tracking; constructing a personalized physiological motion model according to the extracted features, and predicting the motion trail of the patient in a short time; image acquisition is dynamically adjusted based on the model, and blurring caused by movement of the patient is reduced; performing feature fusion on the original image to obtain an intermediate image, and performing adaptive adjustment correction and optimization to generate a terminal image; and finally, fusing the terminal images obtained at the plurality of time points, and outputting a medical image by applying an image enhancement technology. According to the method, the tiny physiological movement of the patient in the medical imaging process is accurately monitored and predicted, image acquisition and compensation are dynamically adjusted according to the tiny physiological movement, the high-definition and high-accuracy medical image is finally generated, and the quality and reliability of the medical image are remarkably improved.
Owner:CHENGDU QIANJUN SPACE TECHNOLOGY CO LTD

Carbamylated polypeptide and application thereof in preparation of rheumatoid arthritis diagnostic kit

The invention discloses a carbamylated polypeptide and application thereof in preparation of a rheumatoid arthritis diagnostic kit. The invention provides a cyclization carbamylation polypeptide as shown in SEQ ID NO. 1 and SEQ ID NO. 2 or a combination of the cyclization carbamylation polypeptide and the combination of the cyclization carbamylation polypeptide and the combination. Tests prove that the cyclized carbamylation polypeptide antigens as shown in SEQ ID NO.1 and SEQ ID NO.2 independently have high diagnostic value for diagnosing the negative RA of the anti-cyclic citrullinated peptide antibody, and respectively have application prospects of being developed into diagnostic kits for the negative RA of the anti-cyclic citrullinated peptide antibody; the combination of SEQ ID NO.1 and SEQ ID NO.2 further improves the diagnosis value of the anti-cyclic citrullinated peptide protein antibody negative RA, and has the application prospect of being developed into the anti-cyclic citrullinated peptide protein antibody negative RA diagnosis kit in a combined manner.
Owner:WEST CHINA HOSPITAL SICHUAN UNIV

Use of a detection reagent for a marker of mixed connective tissue disease

This invention belongs to the field of biomedicine and relates to the application of a detection reagent for a marker of mixed connective tissue diseases. This invention discloses... MEF2C Genes can serve as biomarkers for mixed connective tissue disease; they are found in the peripheral blood of patients with mixed connective tissue disease. MEF2C Gene expression levels were significantly higher in the group than in the healthy group. This invention provides a detection reagent for a mixed connective tissue disease marker, comprising an upstream primer with the nucleotide sequence shown in SEQ ID NO.3 and a downstream primer with the nucleotide sequence shown in SEQ ID NO.4, which can detect... MEF2C Gene expression levels, which can then be used to develop products for the early diagnosis of mixed connective tissue diseases.
Owner:YIMIN BIOMEDICAL TECH (DONGYANG) CO LTD

Non-invasive biopsy multimodal image fusion system and method

PendingCN122090218ATroubleshoot Alignment DifficultiesHigh precisionImage analysisBiological modelsPulmonary noduleMalignancy
This invention relates to the field of medical image processing, specifically to a multimodal medical image fusion system and method, comprising a data preprocessing module, a domain manifold embedding module, a hierarchical adaptive domain alignment network module, a multimodal feature fusion module, and a diagnostic decision module. The system establishes a topological correspondence between EBUS ultrasound, OCT tomography, and DWI functional images through a multidimensional domain manifold embedding structure; employs a hierarchical adaptive domain alignment network to achieve multi-scale feature extraction and precise alignment; designs a topology-preserving multimodal feature fusion mechanism to ensure the complete preservation of key diagnostic information from each modality during the fusion process; and utilizes a dual-path cross-validation decision strategy to improve the stability and reliability of diagnosis. The system inputs the domain-aligned multimodal features into a Transformer network and generates nodule detection and benign / malignant classification results through dual-threshold judgment, achieving accurate and non-invasive diagnosis of small lesions such as pulmonary nodules and early gastrointestinal lesions.
Owner:GUANGDONG OPTO MEDIC TECH CO LTD

Detection method of non-white proteinuria and application of non-white proteinuria in auxiliary diagnosis of metabolic syndrome

The invention belongs to the technical field of biology, and discloses a detection method of non-white proteinuria and application of the non-white proteinuria in auxiliary diagnosis of metabolic syndrome. The non-white proteinuria detection method comprises the following steps: S1, carrying out qualitative analysis on a urine sample to obtain qualitative detection results including urine pH, PRO and BLD; if the BLD is positive, judging that the urine sample is suspected non-white proteinuria; if the BLD is negative, executing the step S2; s2, according to the urine qualitative detection result, a urine sample quantitative detection mode is selected to carry out TPU and MALB quantitative detection on the urine sample, and a quantitative detection result is obtained; and jointly judging whether the urine sample is non-white proteinuria or not according to TPU and MALB quantitative detection results and PRO qualitative detection results. The invention also provides a non-white proteinuria detection system which comprises a laboratory information system, an IS system and a urine quantitative analysis system. The non-white proteinuria detection method can realize identification of white proteinuria and non-white proteinuria in proteinuria, and provides a new way for clinical diagnosis of MetS.
Owner:THE FIRST AFFILIATED HOSPITAL OF ZHENGZHOU UNIV

Metabolic markers of colorectal cancer and their application in the diagnosis of colorectal cancer

The present invention discloses colorectal cancer metabolic markers and their application in diagnosing colorectal cancer. The present invention collects samples from colorectal cancer patients and healthy controls, performs metabolomics analysis, and discovers key metabolic markers related to colorectal cancer and important metabolic pathways related thereto. The present invention discovers for the first time that the above-mentioned metabolic markers show significant differences between colorectal cancer patients and healthy people. Model validation shows that the above-mentioned metabolic markers have high AUC values ​​for diagnosis, and have good predictive effects on early colorectal cancer patients and colorectal precancerous lesions, indicating that the above-mentioned metabolic markers have good clinical use and promotion value.
Owner:THE SECOND AFFILIATED HOSPITAL OF SHANTOU UNIV MEDICAL COLLEGE

Engine supercharging transient response evaluation method and system

PendingCN122282326Aprecise positioningStrong guidanceTurbochargerHydrogen fuel cell
This invention belongs to the field of engine turbocharger testing technology and discloses a method and system for evaluating the transient response of engine turbochargers. The method includes: test preparation, operating condition setting, transient excitation and data acquisition, calculation of speed increment time, calculation of intake pressure to establish efficiency indicators, and two-dimensional diagnostic evaluation. This invention effectively solves the technical problem that existing evaluation parameters cannot distinguish the root cause of response lag, and has advantages such as accurate positioning and strong guidance. It is particularly suitable for the research and optimization of turbocharger systems with stringent transient response requirements, such as hydrogen fuel cell internal combustion engines.
Owner:TIANJIN UNIV

Application of PPP3CA in treatment of renal fibrosis

The invention belongs to the technical field of biological medicine, and particularly relates to application of PPP3CA in renal fibrosis treatment. Researches find that the expression of PPP3CA in fibrotic human renal tubular epithelial cells is up-regulated, and the expression level of PPP3CA in fibrotic kidney tissues of mice is up-regulated; and the renal fibrosis can be obviously relieved by constructing a cell knock-down PPP3CA model and a renal tubule specific PPP3CA knockout mouse to interfere the expression of the renal tubule PPP3CA. Therefore, targeted inhibition of PPP3CA can be applied to prevention, alleviation and treatment of renal fibrosis.
Owner:THE FIRST AFFILIATED HOSPITAL OF ZHENGZHOU UNIV

Biliary atresia differential diagnosis and prognosis marker and application thereof

PendingCN121951023AGood combination performancehigh diagnostic valueMicrobiological testing/measurementMedical automated diagnosisLiver functionsDisease
The invention belongs to the technical field of biological medicine, and particularly relates to a biliary atresia differential diagnosis and prognosis marker and application thereof. The invention provides the application of the KRT17 expression level as a biliary atresia differential diagnosis and prognostic marker for the first time. KRT17 as a single marker has a relatively high diagnostic value (AUC = 0.880) for BA, the efficiency of KRT17 is superior to all conventional clinical liver function indexes, and when KRT17 is combined with alanine aminotransferase for use, the diagnostic accuracy can be further improved to AUC = 0.904, the KRT17 and CX3CL1 are optimally combined, and the AUC value is as high as 0.938. According to the technology, KRT17 is used as a novel biliary atresia differential diagnosis marker, the defects of an existing differential diagnosis system can be made up to a certain degree, the KRT17 is specifically and highly expressed in biliary atresia liver bile duct epithelial cells, normal control and disease control are not expressed, and therefore more accurate differential diagnosis can be provided clinically.
Owner:WOMEN & CHILDRENS MEDICAL CENTER AFFILIATED WITH GUANGZHOU MEDICAL UNIVERSITY

Metabolite composition for evaluating intractable epilepsy of children and application of metabolite composition

The invention discloses a metabolite composition for evaluating children refractory epilepsy and application thereof, and finds that metabolic markers 3-hydroxyvalproic acid, trans-2-octenoic acid, glutamic acid, C-6 ceramide and / or arginine can be applied to diagnosis and / or early prediction of children refractory epilepsy for the first time. Furthermore, it is found that the metabolic marker has an extremely high diagnostic value for children refractory epilepsy, and can diagnose and / or early predict whether a to-be-detected subject suffers from children refractory epilepsy or the risk of suffering from children refractory epilepsy in a high-accuracy, high-sensitivity and high-specificity manner, so that accurate diagnosis and treatment of children refractory epilepsy are effectively promoted; the clinical application prospect is wide.
Owner:WEIFANG MATERNAL & CHILD HEALTH HOSPITAL (WEIFANG MATERNAL & CHILD HEALTH & FAMILY PLANNING SERVICE CENT) +1

Multi-modal image fusion method and device based on graph neural network, and storage medium

The invention discloses a multi-modal image fusion method and device based on a graph neural network and a storage medium in the technical field of medical image processing and artificial intelligence. The method comprises the following steps: acquiring a multi-modal image; performing depth feature extraction on the multi-modal image to obtain a high-dimensional feature map of each modal; dividing the high-dimensional feature graph of each modal into a plurality of graph nodes, calculating the similarity between each graph node and an adjacent node thereof, and constructing an adjacent matrix of a multi-modal graph structure according to the similarity; taking an adjacent matrix as graph topology guidance, capturing a global association relationship and a long-distance dependency relationship of node features in graph nodes, and performing global aggregation according to an attention pooling graph reading function to generate global features; and inputting the global features into the reconstruction network to generate a final fusion image. The technical problems that in the prior art, the modeling capacity for irregular data is limited, and complex spatial association and semantic dependence between multi-modal images are difficult to effectively capture can be solved.
Owner:LULIANG UNIV

A kit for early diagnosis of lung cancer and its application

The present invention belongs to the field of biomedical technology, and particularly relates to a kit for early diagnosis of lung cancer and its application. The kit includes an enzyme-labeled plate coated with a capture antibody, a working solution of an HRP-labeled antibody, an antigen standard, a washing solution, a chromogenic solution, and a termination solution; the heavy-chain amino acid sequence of the monoclonal antibody F6C-1 against the MAPRE2 protein in the capture antibody is as shown in SEQ ID NO.1, and the light-chain amino acid sequence is as shown in SEQ ID NO.2; the heavy-chain amino acid sequence of the monoclonal antibody H3A-2 against the MAPRE2 protein in the HRP-labeled antibody is as shown in SEQ ID NO.3, and the light-chain amino acid sequence is as shown in SEQ ID NO.4. The kit for early diagnosis of lung cancer provided by the present invention has strong specificity, can be used as an auxiliary diagnostic method for lung cancer with high expression of the MAPRE2 protein, and has high diagnostic value.
Owner:CHONGQING MEDICAL UNIVERSITY

An inquiry information processing method and system based on big data analysis

ActiveCN121096594BAddresses issue with missing critical diagnostic informationhigh gold contentMedical data miningMedical automated diagnosisInformation processingOptimization problem
The present application relates to the field of data processing, and more particularly to a diagnosis information processing method and system based on big data analysis. The method comprises the following steps: first, obtaining a low-dimensional embedding vector containing symptom diagnosis associated information; then, constructing a structured covariance matrix by solving an optimization problem, wherein the optimization problem takes the sample covariance matrix as a data fidelity term and takes a graph Laplacian matrix derived from the embedding vector as a regularization term, thereby injecting medical knowledge into the matrix structure; finally, using principal components derived from the structured covariance matrix to reduce the dimensionality of high-dimensional diagnosis features. The present application can effectively retain the symptom combination information which is crucial for clinical diagnosis, avoid the loss of key features, and significantly improve the quality of the features after dimensionality reduction.
Owner:SHENZHEN ZHONGHUI HI-TECH DIGITAL CONSTRUCTION CO LTD

Marker for FSGS diagnosis and treatment and application thereof

The invention relates to the technical field of biological medicine, in particular to a marker for FSGS diagnosis and treatment and application of the marker, and aims at solving the problem that in the prior art, a target biomarker for FSGS abnormal expression is not screened out, related data of FSGS is obtained, and analysis and machine learning screening are conducted on the data, so that the target biomarker for FSGS abnormal expression is obtained. Five key target genes, namely JUN, PLK2, AKR1C3, PTGS2 and HSD11B2, related to the FSGS are obtained, the obtained key target genes are identified and verified, and it is proved that the five key target genes have high indication efficiency on the FSGS and are ideal drug targets; target spot prediction and enrichment analysis are carried out on the active ingredients of the traditional Chinese medicine, the active ingredients of the medicine are combined with key target genes through a molecular docking technology, the binding affinity of the active ingredients of the traditional Chinese medicine such as semen cuscutae and the like and target protein is verified, and the application prospect of the traditional Chinese medicine composition in the aspect of treating FSGS is further verified; the diagnosis and treatment efficiency of the FSGS is powerfully promoted.
Owner:SHANGHAI PUDONG NEW AREA PEOPLES HOSPITAL

Adipose tissue lipid metabolite for evaluating fat health state and detection kit and application of adipose tissue lipid metabolite

PendingCN119643884AEvaluation is direct and fastAccurate individual pathological status dataOrganic active ingredientsMetabolism disorderDiseaseMetabolite
The invention relates to adipose tissue lipid metabolites for evaluating the health state of fat and a detection kit and application of the adipose tissue lipid metabolites. Specifically, the lipid metabolites arachidonic acid and docosapentaenoic acid can be used as markers for evaluating the health state of adipose tissue metabolism; the arachidonic acid can be used for improving obesity metabolic disorder; according to the kit, fat tissue lipid metabolites are rapidly detected, so that the fat tissue is directly and rapidly evaluated; according to the detection kit, the technical requirements on operators are reduced, the operation steps are simplified, and the detection kit can be applied on a large scale, so that early detection and prevention and treatment of obesity-related diseases are improved.
Owner:SHANGHAI TENTH PEOPLES HOSPITAL

Idiopathic atmospheric hydrocephalus biomarker, diagnostic kit and application

The invention discloses an idiopathic atmospheric hydrocephalus biomarker, a diagnostic kit and application, belongs to the technical field of biological medicine, and particularly relates to the idiopathic atmospheric hydrocephalus biomarker which is a protein biomarker and comprises NBL1, TREM2, COL3A1, DPP7, PLA1A, SELENBP1, FGB, CCK, WFIKKN2, KNG1, HBA2, GFRA3 and CSF1. The invention relates to an application of an idiopathic atmospheric hydrocephalus biomarker in preparation of an idiopathic atmospheric hydrocephalus diagnostic kit. Differential proteins are screened through a DIA technology, protein expression is verified through a PRM technology, the idiopathic atmospheric hydrocephalus biomarker is obtained through screening and used for early screening, risk assessment and prognosis judgment of iNPH, early, accurate and objective diagnosis of iNPH is achieved, the clinical diagnosis period is shortened, and the diagnosis and treatment efficiency is improved.
Owner:BRAIN-COMPUTER INTERACTION & HUMAN-COMPUTER INTEGRATION HAIHE LAB

Non-linear mapping parallel imaging reconstruction method and device based on manifold

The invention relates to the technical field of magnetic resonance imaging, in particular to a non-linear mapping parallel imaging reconstruction method and device based on manifold. The method comprises the following steps: acquiring K space data through multiple channels; setting a neighborhood size according to the collected K space data, and adaptively optimizing and adjusting key parameters of high-dimensional mapping; non-linearly related image information and noise components of the K space data are used as feature input and mapped to a higher-dimensional feature space through a popularity method, and a topological relation of the high-dimensional feature space is established; in a high-dimensional feature space, differences between neighborhood points are smoothed through manifold regression, a nonlinear model is established to perform fitting on signal and noise features to complement a down-sampled K space part, and reversible Fourier transform is performed based on reconstructed K space data to recover to an image space. According to the method, the precision and anti-noise performance of the reconstructed image are improved, the application range of the algorithm is expanded, and the problem of low signal-to-noise ratio in low-field-intensity magnetic resonance parallel imaging is solved.
Owner:HEBEI HUIREN MEDICAL EQUIP TECH CO LTD

Biomarker for diagnosing osteoporosis with atherosclerosis as well as construction and application of column diagram

The invention belongs to the technical field of medical biomolecules, and particularly discloses a column diagram construction method for osteoporosis accompanied with atherosclerosis, which specifically comprises the following steps: acquiring a GSE1428 data set, a GSE230665 data set and a GSE1000927 data set from a GEO database; screening out differential expression genes between the osteoporosis and normal tissues and between the atherosclerosis and healthy tissues by using a Limma bag; then performing WGCNA analysis on DEGs, and finally screening differential expression genes by using an LASSO regression algorithm, a random forest and an SVM-RFE algorithm to obtain a potential key common biomarker; based on the key common biomarkers, a column diagram is constructed, an ROC curve is drawn, and the diagnostic ability of candidate common biomarker genes is evaluated to reach 0.99. Based on the column diagram, a prediction system is provided, and a visual basis is provided for clinical diagnosis of osteoporosis with atherosclerosis.
Owner:TIANJIN CENT FOR DISEASE CONTROL & PREVENTION

A biomarker for diagnosing central precocious puberty in women and its application

ActiveCN118883947Bhigh diagnostic valueHas clinical application valueOrgan movement/changes detectionDisease diagnosis
The present invention relates to the field of biomarker technology, and in particular to a biomarker for diagnosing central precocious puberty in women and its application. The present invention provides a biomarker for diagnosing central precocious puberty in women, wherein the marker is one, two or three of Leptin, RBP4 or Chemerin. The present invention has experimentally found that the peripheral blood Leptin, RBP4 and Chemerin levels of female children with CPP are significantly higher than those of healthy children, and the serum Leptin and RBP4 levels change in the early stages of CPP children, suggesting that these three fat factors may be involved in the onset of CPP.
Owner:AFFILIATED HOSPITAL OF NANTONG UNIV