103 results about "Early lung cancer" patented technology

The invention discloses a deep convolutional neural network-based lung cancer preventing self-service health cloud service system. The system comprises a convolutional neural network used for deep learning and training identification, a segmentation module which segments out a lung region from a CT image based on a full convolutional neural network, a deep convolutional neural network used for lung cancer diagnosis classification, and a self-service health cloud service platform used for performing early prevention and treatment according to an identified suspected lung cancer type. According to the system, the automation and intelligentization level of mobile internet-based lung cancer screening can be effectively improved, more citizens can know and participate in self-service health detection, assessment and guidance, the sensitivity, specificity and accuracy of early lung cancer screening and clinical diagnosis are improved, the lung cancer can be early discovered, early diagnosed and early treated, and the self-health management capability is enhanced.

The invention discloses a composition for noninvasive screening of an early lung cancer and application of the composition. The composition comprises three pairs of methylation-specific primer probes of SHOX2 (Short Stature Homebox2) genes, three pairs of methylation-specific primers of PTGER4 (Prostaglandin E Receptor 4) genes and one pair of reference gene primer probes and further comprises three MGB probes corresponding to non-methylation target genes in the SHOX2 genes and three MGB probes corresponding to the non-methylation target genes in the PTGER4 genes. A methylation detection kit for the noninvasive screening of the early lung cancer comprises the composition. Patients suffering from the early lung cancer are screened by detecting promoters of the SHOX2 genes and the PTGER4 genes of free DNA in blood of high-risk lung cancer individuals and methylation conditions of three target sites in gene coding and non-coding areas, and early diagnosis of the lung cancer is aided. The methylation-specific PCR/MSP detection method is simple and convenient in operation and low in time consumption, and the results are easily analyzed.

The invention provides a method for establishing an early lung cancer risk assessment model in combination with an imaging analysis result and belongs to the field of computer aided medicine. On the basis of a traditional risk assessment model, an analysis result based on iconography is combined. A lung nodule benign and malignant judgment result based on CT images is used as one of dangerous factors. The lung nodule benign and malignant judgment result and other dangerous factors such as the smoking history and the family medical history are used as factors of the same level to establish an early-stage lung cancer risk assessment model. Therefore, the accuracy and the reliability of the prediction model are effectively improved.

The invention relates to the field of biological detection, particularly to a group of microRNA biological markers for early lung cancer diagnosis and an application thereof. The microRNA biological marker comprises hsa-miR-125a-5p, hsa-miR-193a-5p, hsa-miR-25, hsa-miR-126 and hsa-miR-34a. The serum miRNA biological markers comprising the 5 miRNAs can not only be particularly applied to early lung cancer detection, but also be applied to advanced lung cancer detection.

The invention belongs to the technical field of biotechnologies and DNA detection, and particularly relates to a DNA methylation qPCR kit for lung cancer detection and a using method thereof, in particular to a kit using plasma free DNA to conduct methylation of qCPR to determine the methylation states of one or more gene targets (such as SHOX2 and SOX17) for lung cancer detection or screening anda using method of the kit. The kit can significantly increase the positive detection rate of early lung cancer and improve specificity of the early lung cancer through an experimental test, detectionsensitivity of biomarkers can be improved to picogram/nanogram level DNA molecules, and improvement of the detection sensitivity is realized by optimizing specific nucleotide sequence primers and DNAprobes and improving a hydrosulphite treatment method of the plasma free DNA.

The invention provides a blood-based noninvasive early lung cancer detection method, which investigates a panel of miRNA levels in a blood or plasma sample. The panel of miRNA includes miR-17, miR-21, miR-24, miR-106a, miR-125b, miR-128, miR-155, miR-182, miR-183, miR-197, miR-199b, miR-203, miR-205, miR-210, miR-221, and a combination thereof. Preferably, the panel of miRNA may include miR-21, miR-128, miR-155, miR-182, miR-183, and miR-197. The inventive method can not only detect stage I lung cancer patients with high accuracy, but also differentiate between all stages of lung cancer patients and lung cancer-free individuals, metastatic and non-metastatic lung cancer patients and monitor the significant changes of miRNA levels during chemotherapy.

The invention provides a kit for testing early lung cancer specific autoantibody enzyme linked immunity, consisting of a solid phase carrier and six recombined bacteriophage liquid which are packed at the surface of the solid phase carrier, contains lung cancer antigenic peptide I, lung cancer antigenic peptide II, lung cancer antigenic peptide III, lung cancer antigenic peptide IV, lung cancer antigenic peptide V and lung cancer antigenic peptide VI, and is equivalently respectively packaged into different enzyme marking holes on the solid phase carrier, wherein each of the six recombined bacteriophage liquid is 100-200mu l. The recombined lung cancer specific antigenic peptide uses T7 bacteriophage to display a lung cancer cDNA library onto the surface of the bacteriophage, is sieved out by means of affinity sieving and serologic analysis, has a capability for testing the autoantibody generated by stimulating tumor in blood serum of a patient, provides an effective testing effect for early lung cancer patients, and has greater clinic application value.

The invention relates to the technical field of medical diagnosis, in particular to a protein fingerprint mass spectrum model for lung cancer early diagnosis. In the model, a protein chip flying time mass spectrum system is used for detecting peripheral serum samples of a normal man and an early lung cancer patient so as to find out a specificity protein peak greatly different from the protein peak of the lung cancer patient; and according to a mass to charge ratio (m/z) of the protein peaks, a protein fingerprint spectrum model of a decision tree by adopting a decision tree algorithm is established. The corresponding m/z ratio of the protein in the serum of the detected man is analyzed by the model so that the lung cancer diagnosis can be realized initially. The forecast accuracy is 71 percent.

The invention discloses a lung cancer related methylation gene combination in plasma and application of the lung cancer related methylation gene combination. According to the lung cancer related methylation gene combination in plasma, the combination comprises SHOX2 and CDO1. The combination further comprises any one or more genes selected from the group consisting of PTGER4, TAC1, HOXA7 and SCT.The composition provided by the invention is used as a detection target to be applied to preparation of a lung cancer auxiliary diagnosis kit. The lung cancer auxiliary diagnosis kit is characterizedby comprising the composition provided by the invention. The kit provided by the invention can improve the detection sensitivity of the biomarker to 310 copies/microliter, and the methylation conditions of the six lung cancer related genes SHOX2, CDO1, PTGER4, TAC1, HOXA7 and SCT are meaningful clinical indexes for potential lung cancer (especially early lung cancer) diagnosis, prognosis evaluation and curative effect monitoring.

The invention discloses a method for detecting an EGFR L858R locus in lung cancer by ddPCR and an application thereof. According to the sequence of an EGFR gene, a pair of amplified primers includingan upstream primer and a downstream primer are designed; according to the mutation sequence of L858R (2573T>G, COSM6224), a probe for detecting a wild type sequence and a probe for detecting a mutation sequence are designed. The primers and the probes are used for ddPCR and used for detecting and analyzing important loci related to targeted medication for lung cancer in ctDNA. Firstly, DNA is extracted from peripheral plasma of lung cancer patients, and the mutation condition of the mutation locus L858R of EGFR is detected by the ddPCR technology, so as to guide the patients to use drugs. Themethod can be used for diagnosis of early-stage lung cancer such as stage I, II and III A of tumor, can detect 0.0625% EGFR gene L858R mutation, and has the sensitivity reaching 10 times or more thatof conventional methods.

The invention relates to the field of image analysis, and particularly relates to an early lung cancer detection and classification integrated system based on deep learning. The system comprises a lung CT image acquisition module, a CT image preprocessing module, a lung image recognition module, a lung nodule measurement module and a lung cancer screening module. The lung image recognition moduledetects and recognizes lung nodules and lung nodule holes in the lung images based on a DSSD_ Xception model, and intercepts lung nodule areas; the lung nodule measurement module is used for measuringlung nodules and lung nodule hole sizes based on the length-width ratio of the connected component bounding rectangle, and outputting a measurement result; and the lung cancer screening module is used for screening early lung cancer based on a preset screening standard according to the measurement result of the lung nodule. According to the invention, the type and probability of early lung cancercan be automatically detected, and the type, size, position and malignant degree of pulmonary nodules can be accurately identified.

The invention discloses a multiple PCR primer system and detection method for detecting lung cancer circulating free DNA (cfDNA) methylation as well as application. The multiple PCR system for detecting lung cancer cfDNA methylation as well as application includes a first round of multiple PCR primer sets and/or a second round of multiple PCR primers, wherein the first round of multiple PCR primersets contains 55 pairs of PCR primers with sequences shown in SEQ ID NO.1-SEQ ID NO.110 in a sequence listing, the sequences of the second round of multiple PCR primers are shown in SEQ ID NO.111-SEQID NO.112. The method for detecting lung cancer cfDNA methylation simultaneously detect 55 methylation sites related to lung cancer at one time, multiple PCR primers have little mutual interference,strong specificity, and high amplification efficiency, besides, the method can reduce the sample loss, reduce detection cost, improve detection efficiency, significantly increase the detection rate ofearly lung cancer by a high-throughput sequencing technology, and is suitable for popularization and application.

The invention belongs to the technical field of molecular biology and clinical detection, and relates to a protein composition containing any two, three, four, five, six or seven selected from the group consisting of CYFRA21-1, NSE, IL-2, IL-8, IFN-gamma, MIP-1beta and VEGF-A. The invention also relates to a ligand composition that binds to the protein specificity in the protein composition, and application of the protein composition or ligand composition in the preparation of a kit for screening, auxiliary diagnosis, treatment monitoring and prognosis of lung cancer. The invention can be usedfor screening, auxiliary diagnosis, treatment monitoring and prognosis judgment of lung cancer, especially screening and auxiliary diagnosis of early lung cancer, which has high sensitivity and highspecificity, and is superior to the detection of single protein markers and clinical commonly-used serum markers CYFRA21-1 and NSE.

The invention relates to the field of biological detection, and concretely to a lung cancer screening associated serum LncRNA marker and an application thereof. The nucleotide sequence of the marker is represented by SEQ ID NO.1. Researches prove that the expression level of the LncRNA marker in lung cancer patients and pulmonary nodule patients is significantly higher that of healthy people, so the LncRNA marker can be used for the screening and the auxiliary diagnosis of early lung cancer, also can be used for the treatment effect evaluation, the drug resistance monitoring and prognosis assessment of the lung cancer, and has a specificity and a sensitivity as a novel lung cancer diagnosis molecular marker.

The invention provides a PET/CT (positron emission tomography/computed tomography)-based lung adenocarcinoma and squamous carcinoma diagnosis model training method and device, and aims to assist in training a PET/CT image-based diagnosis classification neural network by using a multi-task learning method and extracting pathological features through a neural network obtained by diagnosis classification training based on pathological images. According to the method, the lung cancer diagnosis classification precision based on the PET/CT image is improved, and meanwhile, the pathological image is only used as priori knowledge in the training process and does not need to be used as network input in practical application. According to the method, through the concept of multi-scale fusion, the precision of the PET/CT image for lung cancer diagnosis classification is improved, the PET/CT image can be further popularized and applied as a means for early lung cancer diagnosis, and help is provided for diagnosis of a clinician on a patient and a subsequent treatment scheme; and meanwhile, the pathology image is used as a priori knowledge auxiliary scheme, the interpretability of the pathology section is further improved, and pathology doctors can further extract pathology features.

The invention discloses a kit, a device and a method for lung cancer diagnosis. The kit comprises exosome long RNA markers, including one or more of LRRC37A2, TLE4, AZI2, MRPL9, YPEL2, RAB3GAP1, TBC1D23, STK3, IL1B, HMGN1, ERI3, HOPX, CDA, CCBL2, TBK1, RAD54L2, ARPC5, GIMAP5, PLA2G1B, SNHG5 and RPL21. The lung cancer detection method based on the exosome long RNA markers has high sensitivity and high specificity in early lung cancer, and provides an important value for early diagnosis of lung cancer, thereby providing a great help to the prevention and treatment of lung cancer in China.

The invention relates to an exosome ecDNA biomarker detection reagent for the early diagnosis of lung cancer. The biomarker comprises exosome ecDNA biomarkers C-myc, EGFR and CyclinD1, and is used asa biomarker for predicting early lung cancer. The invention provides and verifies that the advantages of rapidness, no harm, high accuracy and high specificity are achieved when the exosome ecDNA is used as a biomarker expression level for the early diagnosis of lung cancer for the first time, and thereby the detection reagent has important significance for the early diagnosis of lung cancer.

The invention discloses a group of gene marker for identifying benign and malignant cases of lung micro nodules and application of the gene marker. The gene marker comprises lung cancer characteristicgenes shown as SEQ ID NO. 1 to SEQ ID NO. 12; the genes are subjected to remarkable differential expression in peripheral blood of micro nodule lung cancer patients and non-lung-cancer patients. Theinvention further discloses application of the gene marker or any combination to preparation of a lung cancer early screening product. The gene marker disclosed by the invention is used for early screening of high-risk lung cancers and has high sensitivity and high specificity; the peripheral blood which is most easily collected clinically is used as a detection sample, a sampling manner is non-invasive and simple and convenient and the detection compliance is high; the gene marker is especially suitable for being matched with imageological diagnosis inspection manners including CT (Computerized Tomography) and the like to screen ultra-early lung cancer of large-scale people, so that the gene marker has a wide application prospect.

The invention belongs to the technical field of markers and detection thereof. The invention discloses a construction method of an ELISA detection kit, a kit and application. The method includes: preparing 1L of a coating liquid, preparing 1L of a 10XPBST washing liquid, preparing 1L of a 1X PBST washing liquid, preparing a confining liquid, preparing an antibody diluent, preparing McIvain's buffer, preparing a developing liquid and preparing a 0.5M phosphate buffer solution. According to the invention, EGFR is verified to be capable of causing immunoreaction of an organism and enabling the organism to generate a corresponding autoantibody, is low in cost, high in specificity, strong in sensitivity, high in accuracy and noninvasive, can be used as a diagnostic biomarker for early lung cancer, is used for distinguishing lung cancer patients from normal people, and is used for identifying different types of lung cancer patients from a normal control group; the EGFR autoantibody also hasa diagnostic value for early lung cancer, and can be combined with a clinical indicator CEA to improve the lung cancer diagnosis accuracy.