34results about How to "High diagnostic efficiency" patented technology

The invention discloses a two-dimensional image and CR or MR image three-dimensional fusion method. The method comprises the steps that three-dimensional geometric structure information of a CT or MRI structure image is used for combining multi-angle two-dimensional images for human body three-dimensional target image reconstruction, and then target image and MR image three-dimensional multi-modal fusion is achieved. According to the three-dimensional medical image fusion technology, the purpose of two-dimensional image three-dimensional complex structure positioning is achieved, and more precise focus positioning is provided; in addition, the two-dimensional image and the CT or MR image are subjected to three-dimensional fusion, multi-modal image system construction is achieved, more abundant resource information is provided for clinical disease diagnosis, and the diagnostic efficiency is improved.

The invention discloses an adaptive multi-site scanning imaging method based on deep learning and a system thereof. The method is applied to a multi-modal imaging device mainly based on the nuclear medicine, and comprises the following steps of step A, for multiple target sites of an imaging target object, conducting single-modal or multi-modal reconnaissance scanning imaging; step B, utilizing image analysis software based on a deep learning technology to analyze the reconnaissance scanning imaging data in step A, and combined with relevant prior information, detecting a local area which needs further focus imaging and quantifying importance or risks thereof; step C, based on the results of step B, selecting an optimized process and parameters to perform the next scanning. The adaptive multi-site scanning imaging method maximizes the image diagnostic value contributed by unit scanning time and / or a radiation dose, achieves optimized precision image inspection for individuals through multi-site scanning imaging application on tumors to improve the diagnostic performance, and has an important practical value.

A transformer winding fault diagnosis method based on wireless identification sensing includes the following steps: collecting transformer winding vibration signals in a normal state and when a fault occurs; denoising the transformer winding vibration signals by using singular entropy, and randomly dividing the denoised transformer winding vibration signals in the normal state into two groups, where one group is training data, and the other group is original measurement data; using the denoised transformer winding vibration signals obtained when the fault occurs as original threshold data; reconstructing the original threshold data to obtain reconstructed threshold data, and obtaining a transformer winding residual error threshold when the fault occurs; and reconstructing the original measurement data to obtain reconstructed measurement data, obtaining corresponding residual error data, and comparing the residual error data with the residual error threshold, to implement fault diagnosis on the transformer winding. The present invention implements remote, wireless, and unmanned fault diagnosis on a transformer winding. The diagnosis efficiency is high, the workload of a maintenance person is reduced, and the running efficiency of a transformer is increased.

An X-ray CT apparatus, wherein a drum type rotation frame is rotatably supported by a fixed circular frame so as to surround an outer surface of the drum type rotation frame through a plurality of bearings provided between an inner surface of the fixing circular frame and an outer surface of the drum type rotation frame, for example in ring-like configuration. When the drum type rotation frame receives a large centrifugal acceleration due to a high speed rotation, outside expansion of the drum type rotation frame can be constrained due to both the rigidity of the fixed frame and the rigidity of the plurality of bearings provided on the outer surface of the rotation frame, thereby to maintain the relative positions of the X-ray tube and the X-ray detector and prevent deterioration of reconstructed images.

The invention relates to a navigation method and system for a lung biopsy bronchoscope. The method comprises the following steps: acquiring CT image data; inputting the CT image data into the trained deep learning pulmonary nodule recognition neural network model, and outputting to obtain pulmonary nodule data; performing endoscope image space three-dimensional model reconstruction on the CT image data by using a virtual endoscope technology, and performing focus marking in an endoscope image space three-dimensional model in combination with pulmonary nodule data; selecting a focus mark in the endoscope image space three-dimensional model, and performing operation path planning; and mapping the pose of the bronchoscope catheter from the actual physical coordinate system to an endoscope image space, and carrying out registration from the actual physical position space to the image space. Compared with the prior art, the invention has the advantages of integration of deep learning nodule diagnosis, CT reconstruction and virtual endoscope navigation, accurate positioning, high diagnosis efficiency and the like.

The invention relates to the field of medical science, and provides a biomarker for hepatocellular carcinoma related detection, particularly a biomarker for detecting HBV related hepatocellular carcinoma. The biomarker comprises an insulin-like growth factor binding protein 7 (IGFBP7) and an alpha fetoprotein (AFP). A method for detecting hepatocellular carcinoma, based on the biomarker namely the IGFBP7 and the AFP, comprises a step of carrying out judgement by measuring a marker IGFBP7 gene promotor methylation level and detecting the sensitivity of the marker AFP for being combined with serum IGFBP7 gene promoter methylation. According to biomarker, the AFP is combined with the IGFBP7 gene promoter methylation, so that the traditional detection of single indexes is changed, and the efficiency of HCC diagnosis is increased.

The invention discloses an artificial intelligence assisted prostate tumor early diagnosis method based on surface enhanced Raman spectroscopy. The method comprises the following steps of: collectinga serum sample; adopting a Raman spectrometer for detection; performing graphic analysis and data processing on an acquired Raman spectrum signal; selecting a biological tissue Raman spectrum concentration range of 400-1800cm<-1> for analysis, and preprocessing an original spectrum acquired by a spectrograph through Origin Pro 8 software, i.e. performing background reduction and spectrum area homogenization, drawing a serum average Raman spectrum, and then comparing changes and differences of related Raman characteristic peaks, thus finally obtaining a diagnosis result of prostate tumor earlydiagnosis. The method provided by the invention is higher in sensitivity and specificity, and unnecessary needle biopsy and missed diagnosis caused by an existing screening diagnosis method are reduced.

The invention discloses a peripheral blood methylation gene and IDH1 combined detection and diagnosis model for lung cancer. The invention provides application of methylated SHOX2 gene, methylated PTGER4 gene and IDH1 protein as markers in preparation of products for diagnosis or auxiliary diagnosis of lung cancer, and constructs a three-marker combined lung cancer diagnosis model. Experiments prove that: compared with an incorporated single factor, the diagnosis efficiency of the combined diagnosis model is remarkably enhanced. Therefore, the diagnosis efficiency of the lung cancer can be improved by combined detection blood markers.

The invention provides a combined antigen comprising three mycobacterium tuberculosis antigens and an application of the combined antigen to preparation of a reagent for diagnosing active tuberculosis. The combined antigen comprises Rv3871, Rv3876 and Rv3879. Corresponding antibody detection methods are established by the aid of the three antigens and used for detecting corresponding antibody levels in biological samples, and the three detected antibody levels are particularly higher in sputum smear negative / sputum culture positive tuberculosis patients. A pulmonary tuberculosis diagnosing method is established by the aid of the combined antigen, and a positive sample is defined in such a manner that antibody levels corresponding to two or more antigens reach a positive judgment value. Verification of a lot of clinical samples indicates that the diagnosing method has the high sensitivity and the high specificity for sputum smear positive / sputum culture positive, sputum smear negative / sputum culture positive and sputum smear negative / sputum culture negative tuberculosis patients.

The invention provides an ultra-small functional nanocluster. A nanoculster structure is formed by taking GSH as a template and chelating sulfydryl and carboxyl on the surface of GSH with Au atom andgadolinium Gd atom; two types of atoms are simultaneously coated in the nanoculster structure. The invention also provides an ultra-small functional nanoprobe with the surface modified by cNGR and a preparation method thereof. The ultra-small functional nanoprobe has the capability of specifically identifying tumor angiogenesis; the quantum confinement effect of the Au atom is used for generatingfluorescence and absorbing X-ray according to the adsorption coefficient, so that fluorescence imaging and CT imaging can be achieved; the Gd atom is used for shortening longitudinal relaxation time of free water protons and enhancing MR contrast ratio, so that the application of the ultra-small functional nanoprobe in the multimodal imaging of the tumor angiogenesis can be achieved. The preparednanoparticles are small in size being smaller than 10nm, high in biocompatibility and low in toxicity; through the application of modular assembly performance of the nano material, efficient synergy of multiple functions is achieved; the ultra-small functional nanoprobe is high in preparation yield and is suitable for large-batch production.

The invention provides a colloidal gold lateral flow test strip for breast cancer detection, a preparation method of the colloidal gold lateral flow test strip and a colloidal gold lateral flow test strip for simultaneously detecting breast cancer and cervical cancer and belongs to the technical field of immuno-chemical detection. The colloidal gold lateral test strip comprises a PVC bottom plate,a nitrocellulose film, a sample pad, a conjugate pad and an absorption pad, and can be used for detecting miRNA markers (miR-16 and miR-191) and protein markers (CA153 and CA125) of breast cancer. The invention further provides a colloidal gold lateral test strip for simultaneously detecting breast cancer and cervical cancer, which can overcome the interference (hybridization among components) ofa background signal to realize specific detection on two different types of tumor marker groups, including miRNA groups and protein, of the cervical cancer and breast cancer, and has the detection specificity of 100 percent.

The present invention provides a diagnosis system for vehicular DC charging relay, the system comprises a controller, two resistor clusters R1 and R2, and a switch S, wherein, two resistor clusters R1 and R2 are bridging in a serially connected way in between the DC charging high voltage cables of the vehicle, the resistor cluster R1 consists of two serially connected sub-resistors, and the controller is able to measure a voltage V1 at a common terminal of the two serially connected sub-resistors via a first voltage detection port, the resistor cluster R2 consists of two serially connected sub-resistors, and the controller is able to measure a voltage V2 at a common terminal of the two serially connected sub-resistors via a second voltage detection port, the controller is able to execute a diagnosis operation, and the diagnosis operation is based on the measurements of the voltages V1 and V2.

The invention discloses a GIS-based power equipment distributed multistage intelligent fault diagnosis system, which comprises an information acquisition module for collecting the macroscopic operation characteristics and the insulation operation characteristics of the power equipment through an SCADA and insulation online monitoring system; an initial diagnosis analysis module which is used for searching the equipment abnormal variable X from a real-time database and then carrying out preliminary diagnosis by utilizing an intelligent fault diagnosis model to obtain a preliminary diagnosis result; a comprehensive diagnosis and analysis module which is used for searching the detected information of other equipment related to the abnormal variable X, and then performing comprehensive diagnosis by utilizing an expert system in combination with the preliminary diagnosis result; and a diagnosis result display module which is used for displaying the fault information in a power distributionnetwork GIS in real time and sending out an alarm signal. According to the system, the real-time state data of the power system can be effectively utilized, according to the steps of determining the node closest to the fault, determining whether the fault is the single-line grounding fault and determining the fault line, the detection and positioning of the single-line grounding fault line are realized, and the safe operation of the system is facilitated.

A method and device improve efficiency, depth and reliability of diagnosing technical condition of highly complex objects. The technical effect is achieved by signals received from a diagnosed object (DO). These signals are transformed into a technical condition initial estimate vector for the DO elements. Then, technical condition estimates for the OD elements are specified through a cyclical process and by using a reverse logical model and a direct logical model. A technical condition vector estimate is formed after the cyclical process is completed, and its variable components are used for deciding on technical condition of the diagnosed object elements. The device comprises an interface unit which inputs serve for connecting to the DO data outputs, a measuring unit, an initial estimate forming unit, a switching unit, a reverse triplex logical model and a direct triplex logical model, a result interpretation unit and a control unit.

A transformer winding fault diagnosis method based on wireless identification sensing includes the following steps: collecting transformer winding vibration signals in a normal state and when a fault occurs; denoising the transformer winding vibration signals by using singular entropy, and randomly dividing the denoised transformer winding vibration signals in the normal state into two groups, where one group is training data, and the other group is original measurement data; using the denoised transformer winding vibration signals obtained when the fault occurs as original threshold data; reconstructing the original threshold data to obtain reconstructed threshold data, and obtaining a transformer winding residual error threshold when the fault occurs; and reconstructing the original measurement data to obtain reconstructed measurement data, obtaining corresponding residual error data, and comparing the residual error data with the residual error threshold, to implement fault diagnosis on the transformer winding. The present invention implements remote, wireless, and unmanned fault diagnosis on a transformer winding. The diagnosis efficiency is high, the workload of a maintenance person is reduced, and the running efficiency of a transformer is increased.

The invention relates to the technical field of biological medicines, and discloses an application of a combined gene in preparation of a product for diagnosing esophageal squamous carcinoma. The combined gene comprises the following genes of a CCL20 gene, a GSTP1 gene, an HSPB1 gene, a KRT14 gene, a KRT15 gene, an S100A8 gene, an S100A9 gene and a TACSTD2 gene. The invention also discloses an application of the combined gene in preparation of a pharmaceutical composition for treating the esophageal squamous carcinoma. Compared with single gene expression detection of the esophageal squamous carcinoma in the prior art, the combined gene has higher specificity and higher diagnosis efficiency, can significantly improve the detection sensitivity and specificity, can accurately, conveniently and efficiently perform esophageal squamous carcinoma early diagnosis and large-scale screening, and fills up the blank of an existing diagnosis technology, so that effective treatment measures are provided for esophageal squamous carcinoma patients in time, and prognosis is improved.

A network diagnosis method, a cloud intelligent robot, a network device and a private network, relate to the technical field of communications, and are used for solving the technical problems of having low diagnosis efficiency and leakage risk for a private network in the prior art. The method comprises: an cloud intelligent robot transmitting a network monitoring instruction to a network device in a private network; receiving operation information transmitted by the network device according to the network monitoring instruction; diagnosing the network device according to the operation information to obtain a diagnosis result; and initiating a network configuration information update of the private network according to the diagnosis result.

The invention discloses an application of the expression level of Gremlin-1 in blood plasma in a product of a diagnostic marker for detecting hepatocellular carcinoma. The expression of the Gremlin-1in the blood plasma in a tissue specimen of the hepatocellular carcinoma HCC is mainly located at the interstitial-tumor junction. The invention further discloses application of the Gremlin-1 in the blood plasma in screening or auxiliary diagnosis of hepatocellular carcinoma products. By applying the technical scheme of the invention, a product such as a kit for detecting the diagnostic marker ofthe hepatocellular carcinoma can be designed, and a product for screening or assisting in diagnosing the hepatocellular carcinoma can also be designed, so that the diagnostic efficiency and the clinical transformation value are further improved.

The present invention provides a diagnosis system for vehicular DC charging relay, the system comprises a controller, two resistor clusters R1 and R2, and a switch S, wherein, two resistor clusters R1 and R2 are bridging in a serially connected way in between the DC charging high voltage cables of the vehicle, the resistor cluster R1 consists of two serially connected sub-resistors, and the controller is able to measure a voltage V1 at a common terminal of the two serially connected sub-resistors via a first voltage detection port, the resistor cluster R2 consists of two serially connected sub-resistors, and the controller is able to measure a voltage V2 at a common terminal of the two serially connected sub-resistors via a second voltage detection port, the controller is able to execute a diagnosis operation, and the diagnosis operation is based on the measurements of the voltages V1 and V2.

The invention provides a rifampicin drug-resistant tuberculosis molecular marker, a detection reagent and an application thereof. Involved in the field of biomedical technology. The molecular markers include TRIM9, TRIM21 and TRIM56 genes and expression products thereof; the expression of the TRIM9, TRIM21 and TRIM56 genes is down-regulated in rifampicin-resistant tuberculosis patients. The invention can quickly, efficiently and sensitively identify rifampicin drug-resistant tuberculosis patients, and can be used for the screening of rifampicin drug-resistant tuberculosis.

The invention discloses an adaptive multi-part scanning imaging method and system based on deep learning, which is applied to multi-modal imaging equipment mainly based on nuclear medicine, and includes the following steps: Step A, aiming at multiple imaging targets Perform single-modal or multi-modal reconnaissance scanning imaging of the target site; step B, use image analysis software based on deep learning technology to analyze the reconnaissance scanning image data in step A, and combine relevant prior information to detect further Focus on the local area of ​​imaging and quantify its importance or risk; step C, based on the results of step B, select the optimized process and parameters to implement the next scan. The self-adaptive multi-part scanning imaging method proposed by the present invention maximizes the image diagnostic value contributed by the unit scanning time and / or radiation dose, realizes individual optimized precise image inspection for multi-part scanning and imaging applications such as tumors, and improves diagnostic efficiency. Has important practical value.

The invention discloses a miRNA marker for diagnosis and treatment of melanoma and a related product thereof. The miRNA marker is a combination of miR-450a and miR-675. The product for diagnosis of the melanoma comprises a chip, a kit and a preparation, wherein the chip, the kit and the preparation comprise a probe for specifically recognizing the miR-450a and the miR-675 or a primer, probe or chip for specifically combining the miR-450a and the miR-675. According to the miRNA marker and the related product thereof, experimental verification shows that the miRNA marker has better diagnosis efficiency, and the combination of the miR-450a and the miR-675 has a synergistic effect, so that the miRNA marker and the related product thereof can be used for diagnosing and treating the melanoma.

The invention discloses an auxiliary diagnostic reagent for bronchial asthma. The reagent for detecting proline is applied to preparation of an auxiliary diagnostic reagent for bronchial asthma. The invention also discloses application of the reagent for extracting and detecting proline in preparation of the auxiliary diagnostic reagent for bronchial asthma. The auxiliary diagnostic reagent for bronchial asthma comprises a reagent for extracting proline from serum and a reagent for quantitatively detecting proline. It is found for the first time that the plasma proline level of an asthma patient is higher than that of a normal person, and statistical significance is achieved. When the cutoff value of proline is 38.7 ug / mL, the area under an ROC curve for diagnosing asthma is 0.951 (P is less than 0.0001), which indicates that the diagnosis efficiency is relatively high. Plasma proline is used as a biomarker, a specimen is easy to take, alveolar lavage is not needed, the method belongs to noninvasive examination, early diagnosis of asthma can be assisted, a proline detection method is economical and easy to carry out, and a potential target spot is provided for diagnosis and treatment of bronchial asthma.

A method and device improve efficiency, depth and reliability of diagnosing technical condition of highly complex objects. The technical effect is achieved by signals received from a diagnosed object (DO). These signals are transformed into a technical condition initial estimate vector for the DO elements. Then, technical condition estimates for the DO elements are specified through a cyclical process and by using a reverse logical model and a direct logical model. A technical condition vector estimate is formed after the cyclical process is completed, and its variable components are used for deciding on technical condition of the diagnosed object elements. The device comprises an interface unit which inputs serve for connecting to the DO data outputs, a measuring unit, an initial estimate forming unit, a switching unit, a reverse triplex logical model and a direct triplex logical model, a result interpretation unit and a control unit.

The invention discloses an application of protein markers in combination in diagnosis of type 2 diabetes mellitus and type 2 diabetic nephropathy. The protein markers are Cathepsin D, alpha2-Macroglobulin and CD324. The protein markers can be jointly used for diagnosing and distinguishing healthy people from type 2 diabetic patients, diagnosing and distinguishing healthy people from type 2 diabetic nephropathy patients, diagnosing and distinguishing type 2 diabetic patients from type 2 diabetic nephropathy late patients, and diagnosing and distinguishing type 2 diabetic nephropathy early patients from type 2 diabetic nephropathy late patients, and is high in diagnosis efficiency. The protein markers have a prospect of being developed into a kit for diagnosing type 2 diabetes and type 2 diabetic nephropathy.

The invention provides a rifampicin drug-resistant tuberculosis molecular marker, a rifampicin drug-resistant tuberculosis detection reagent and application thereof, and relates to the technical field of biomedicine. The molecular marker comprises a TRIM9 gene, a TRIM21 gene, a TRIM56 gene and expression products of the TRIM9 gene, the TRIM21 gene and the TRIM56 gene. The expression of the TRIM9, TRIM21 and TRIM56 genes in a rifampicin drug-resistant tuberculosis patient is reduced. The rifampicin drug-resistant tuberculosis molecular marker can be used for identifying rifampicin drug-resistant tuberculosis patients more quickly, efficiently and sensitively, and can be used for screening rifampicin drug-resistant tuberculosis.

Disclosed is a method of distinguishing type III hyperlipidemia in the WHO-classified hyperlipidemia types (hereinafter referred to as type III) from other types of hyperlipidemia, which is a simpler method and has a higher diagnostic efficiency than conventional methods. The method of assisting the determination of type III hyperlipidemia includes the steps of: measuring the apoB-48 value, TG value and LDL-C value in a blood sample isolated from a living body; and calculating a ratio of the apoB-48 value divided by the TG value and a ratio of the apoB-48 value divided by the LDL-C value. In cases where both the ratio of the apoB-48 value divided by the TG value and the ratio of the apoB-48 value divided by the LDL-C value are higher than the respective cut-off values, it indicates that the living body is likely to have type III hyperlipidemia.