107 results about "Node metastasis" patented technology

The present invention describes a method for identification and labeling of sentinel lymph nodes (SLNs) and the presence or absence of lymph node metastases as an important diagnostic and prognostic factor in early stage cancers of all types. The method, know as Molecular Lymphatic Mapping, uses traditional dye/radioactive tracer based techniques in conjunction with a nucleic acid marker to identify and label the SLN, not only for current diagnostic methods, but for archival purposes. In addition, MLM can be used to deliver a therapeutic gene or genes to the SLN to activate tumor immunity to tumor cells, and/or to inhibit tumor metastases. The methods may be combined with therapeutic intervention including chemotherapy and radiotherapy.

The invention discloses a nasopharyngeal carcinoma structured image report and data processing system and a nasopharyngeal carcinoma structured image report and data processing method. The system comprises a clinical data collection module, a fine image analysis and report module, a comprehensive processing module and a clinical decision module, is mainly used for inputting and analyzing nasopharyngeal carcinoma imaging diagnosis report data and comprehensively and systematically recording the nasopharyngeal carcinoma invasion surrounding anatomical structure and lymph node metastasis conditions in a structural data form, and establishes a nasopharyngeal carcinoma structural image report standard for constructing a nasopharyngeal carcinoma image big database and a nasopharyngeal carcinomaartificial intelligence prediction model. According to the system, an MR fine film reading database is established to standardize a nasopharyngeal carcinoma image report, and a set of a nasopharyngealcarcinoma online clinical decision platform is developed on the basis to further assist nasopharyngeal carcinoma staging and typing, treatment scheme recommendation and prognosis prediction, so thatclinicians are helped to well formulate a treatment scheme according to an MRI image evaluation result.

The embodiment of the invention provides an automatic lymph node sketching method and device, and the method comprises the steps: obtaining a patient image of a to-be-sketched lymph node, carrying outthe preprocessing of the patient image, and obtaining an interested region image; inputting the region-of-interest image into a lymph node segmentation model to obtain a binary image representing a lymph node region; performing post-processing on the binary image representing the lymph node area to obtain a lymph node sketching result, wherein the lymph node segmentation model is obtained by taking a preprocessed patient image sample as a first channel input, taking lymph node transition probability information based on priori knowledge as a second channel input, and taking lymph node data manually sketched by a doctor corresponding to the patient image sample as a sample label for training. According to the embodiment of the invention, the problems of long consumed time, inaccurate sketching and low segmentation precision of the existing lymph node sketching method can be effectively solved.

The disclosure generally relates to the preparation of representative samples from clinical samples, e.g., tumors (whole or in part), lymph nodes, metastases, cysts, polyps, or a combination or portion thereof, using mechanical and/or biochemical dissociation methods to homogenize intact samples or large portions thereof. The resulting homogenate provides the ability to obtain a correct representative sample despite spatial heterogeneity within the sample, increasing detection likelihood of low prevalence subclones, and is suitable for use in various diagnostic assays as well as the productionof therapeutics, especially 'personalized' anti-tumor vaccines or immune cell based therapies.

The invention discloses a papillary thyroid carcinoma lymph node metastasis prediction method based on Transform-MIL. The method comprises the following steps: S1, extracting the characteristics of patch in WSI by using a lightweight ViT network; s2, selecting a key path by adopting a clustering-based strategy; s3, constructing a Transform-MIL model, learning relationships among instances from multiple aspects through a multi-head self-attention mechanism, and embedding instance-level features into packet representation; s4, combining a thyroid papillary set and a lymph node metastasis data set, and helping a Transform-MIL model to learn and predict lymph node metastasis through mutual knowledge distillation; according to the method, the Transform-MIL model is constructed, the instance-level features are better embedded into the packet representation, the morphological similarity between the tumor cells and the lymph node metastasis cells is fully utilized, and the knowledge of the relationship between the two data sets is transmitted by taking the attention map as a medium, so that the prediction accuracy of the lymph node metastasis histopathology image is improved.

The invention discloses an intelligent diagnosis method for rectal cancer lymph node metastasis, and relates to the field of intelligent medical imaging diagnosis, and the method specifically comprises the following steps: carrying out the preprocessing of CT image data of the abdomen of a patient, reading a DCM image file, converting the file into a three-dimensional array matrix, and carrying out the data stipulation of the matrix; sending the stipulated data as a training sample to an established convolutional neural network model (CNN) for supervised learning, classifying the CT images byusing the classification model, and detecting tumor pictures contained in the images; constructing an improved AGs-Unet network model, sending the tumor original image and the tumor mask image data into the segmentation model for training, and using the model to segment a tumor area; extracting radiology characteristic data from the tumor image area, wherein the radiology characteristic data comprises texture characteristics, gray scale characteristics and morphological characteristics; selecting effective feature data to train a support vector machine SVM classification model, and using the classification model to predict and diagnose whether lymph node metastasis exists in rectal cancer or not. The rectal cancer tumor segmentation precision and lymph node metastasis diagnosis accuracy are improved.

The invention discloses a prediction method and system for latent N2 lymph node metastasis of surrounding NSCLC, and the method comprises the steps: collecting the imaging omics features and clinicalpathological features of a primary lesion in a clinical staging N1 stage and a pulmonary portal lymph node at the same side in PET-CT; establishing a Nomogram model by utilizing the imaging omics characteristics and the clinical pathological characteristics; scoring a patient in clinic based on the Nomogram model to obtain a corresponding risk probability coefficient; and utilizing the risk probability coefficient to predict and evaluate the probability of occurrence and transfer of the latent N2 lymph node. According to the invention, the image omics features are extracted through the convolutional neural network, so the accuracy and reliability of the classification or prediction of the imaging omics are further improved; the Nomogram based on the imaging omics can provide personalized information about whether lymph node metastasis exists or not according to the actual situation of each non-small cell lung cancer patient more visually and more accurately, so the unnecessary medicalexamination and operation of the patient are avoided.

The invention discloses a reagent for auxiliarily diagnosing lung cancer lymph node metastasis, comprising 8 antibodies which are used for detecting 8 protein markers which are MMP1 (matrix metalloproteinase-1), TIMP1 (tissue inhibitor of metalloproteinases metallopeptidase inhibitor 1), IQGAP1 (IQ motif containing GTPase activating protein 1), TPX2 (targeting protein for Xklp2), uPA (Urokinase-type plasminogen activator), Cathepsin-D, Fascin and pIgR/SC (polymeric immunoglobulin receptor/secretory component). By adopting the 8 antibodies and an immunohistochemical staining result, lung cancer lymph node metastasis can be auxiliarily diagnosed, and the reagent is expected to be used for the risk estimation of lung squamous cell cancer lymph node metastasis and the prognostic prediction. The reagent has high creditability, strong practicability and clinical use value based on the clinical routine immunohistochemical staining technology when the reagent is used for auxiliary diagnosis.

The invention discloses a breast cancer patient axillary lymph node metastasis prediction model and a construction method thereof. The artificial intelligence prediction model for axillary lymph nodemetastasis of a breast cancer patient is established through employing an artificial intelligence machine learning algorithm based on the magnetic resonance image data and clinical feature data of thebreast cancer patient. The prediction model has the advantages of being accurate, simple, convenient, non-invasive and the like, can effectively evaluate preoperative axillary lymph node metastasis of a breast cancer patient, is helpful for assisting breast cancer clinical diagnosis and treatment decisions, reducing unnecessary axillary lymph node cleaning operations of the patient, reducing operative complications and improving the life quality of the patient, has higher prediction efficiency and clinical income, and has important guiding significance for guiding clinical treatment strategies and enhancing clinical treatment intervention and subsequent individualized follow-up visit.

The invention discloses a method for constructing a lymph node metastasis prediction model of a breast cancer patient based on radiomics. The method comprises the following steps: acquiring magnetic resonance image data and clinical feature data of the patient; extracting image features based on the magnetic resonance image data; screening the image features by using a random forest algorithm to obtain a plurality of key image features, and establishing an image feature prediction model based on the key image features by using a support vector machine algorithm; performing single-factor analysis screening on the clinical feature data to obtain key clinical features, and establishing a clinical feature prediction model according to the key clinical features by adopting a support vector machine algorithm; and establishing a lymph node metastasis comprehensive prediction model according to the key image features and the key clinical features by adopting a support vector machine algorithm. According to the embodiment, the model is established by adopting the random forest algorithm and the support vector machine algorithm, the prediction model can be established based on the structure risk minimum principle, and the problem of over-learning can be avoided, so that the constructed prediction model is more stable and accurate.

The invention provides circPTEN1 for a tumor treatment target and a diagnosis biomarker and application of circPTEN1, and belongs to the technical field of biology. A nucleotide sequence of the circPTEN1 for the tumor treatment target and the diagnosis biomarker is shown as SEQ ID NO: 1, and the circPTEN1 is a novel circular RNA formed by reversely splicing the first exon to the fifth exon of PTEN mRNA. High expression of the circPTEN1 remarkably inhibits migration and invasion of colorectal cancer cells, the expression level of the circPTEN1 is in negative correlation with lymph node metastasis and distant metastasis of a colorectal cancer patient, and prognosis of the colorectal cancer patient with low expression of the circPTEN1 is poor. Therefore, the circPTEN1 is applied to tumor treatment, tumor diagnosis and tumor prognosis evaluation as the tumor treatment target and the diagnostic biomarker, and a new thought and a new strategy are provided for treatment-related drugs and diagnostic products.

The invention discloses a lung cancer TNM staging acquisition method. The method comprises the following steps of identifying a target nodule in a medical image; acquiring long and short paths of thetarget nodule, and generating T stages at least based on the long and short path; identifying abnormal lymph nodes in the medical image, and generating N stages by judging whether the abnormal lymph nodes have metastasis or not; acquiring whether the target nodule has distant metastasis or not, and generating M stages according to whether the target nodule has distant metastasis or not; and generating a TNM stage according to the T stage, the N stage and the M stage. According to the method, a nodule recognition model, a nodule segmentation model and a lymph node metastasis recognition model are trained, the information outputted by the models is utilized to automatically generate a T stage and an N stage, and whether distant metastasis information is generated into an M stage or not is judged in combination with doctor input or by accessing medical records and the like. According to the method, TNM staging generation efficiency is effectively improved, a doctor can conveniently and quickly know the illness state of a patient, and diagnosis efficiency is improved.

The invention belongs to the field of image analysis, particularly relates to a lymph node metastasis image analysis system, method and equipment based on deep learning, and aims to solve the problem that in the prior art, whether lymph node metastasis occurs in a non-small cell carcinoma image cannot be well predicted noninvasively. The method comprises the steps of obtaining a to-be-analyzed CT image containing a lesion microenvironment, obtaining an imaging sign and clinical information of the same subject as the CT image, extracting one-dimensional CT image features and one-dimensional clinical information features respectively, performing feature enhancement and normalization processing, performing fusion through a full connection layer to generate a fusion feature vector, and classifying the fused feature vectors to obtain an analysis result. The non-small cell lung cancer lymph node metastasis image data classification method achieves classification of non-small cell lung cancer lymph node metastasis image data, has good robustness and generalization ability compared with an existing traditional vector model based on predefined image features, and effectively improves the prognosis effect of a patient.

The invention provides a nanoparticle targeting breast cancer cell and lymph node metastasis focus, and belongs to the technical field of bioscience and drug carriers. The nanoparticle comprises phospholipid, cholesterol ester, a near infrared probe, a hyaluronic acid-phospholipid compound and alpha spiral polypeptide. The nanoparticle can effectively mark breast cancer cells and can effectively target lymph nodes, the lymph nodes with tumor metastasis can be distinguished from inflammatory lymph nodes and normal lymph nodes through the distribution difference of photoacoustic microimaging signals of the nanoparticle in the lymph nodes in different states, and the accuracy of breast cancer lymph node metastasis identification is improved. The invention further provides a preparation methodand application of the nanoparticle targeting breast cancer cell and lymph node metastasis focus.

The invention relates to a kit for detection and/or treatment on lymph node metastasis. The kit comprises: (1) a detection reagent for detecting expression of FGL1 (fibrinogen like 1), and/or (2) a treatment reagent for inhibiting expression or actions of FGL1. The invention further relates to application of FGL1 or a derivative thereof in preparing a medicine or kit for detection and/or treatmenton lymph node metastasis. The FGL1 can be not only used as a molecular marker of lymph node metastasis, but also applied to preoperative diagnosis and prognosis of lymph node metastasis, and even iscapable of inhibiting lymph node metastasis by inhibiting the FGL1, and thus a treatment function can be achieved.

The invention discloses a breast cancer sentinel lymph node metastasis prediction method and system and a storage medium, and the method comprises the steps: obtaining a WSI with a label as a training data set, and carrying out the preprocessing, and obtaining an image block set; constructing a WSI classification model; pre-training a feature extractor by using the image block set to obtain a feature vector set; inputting the feature vector set into a prototype clustering module, and extracting a plurality of prototypes through clustering; the breast cancer sentinel lymph node WSI is divided into image blocks, and then the image blocks are input into a feature extractor to extract image block features; matching the image block features with a prototype input feature fusion module, generating a soft distribution histogram, and constructing a feature vector of breast cancer sentinel node WSI; and sending the feature vector of the breast cancer sentinel lymph node WSI into a full connection layer to obtain a WSI classification score, and performing transfer judgment. The method can better solve the problem of micro-metastasis identification while maintaining accurate identification of macro-metastasis, so that breast cancer sentinel lymph node metastasis can be accurately diagnosed.

The invention discloses application of EIF5A2 to preparation of an esophageal squamous cell carcinoma prognosis reagent. Real-time quantitative PCR (Polymerase Chain Reaction) detection data shows that expression of the EIF5A2 in esophageal squamous cell carcinoma tissues is obviously higher than that in corresponding non-tumor tissues. An immunohistochemical data analysis result shows that expression of the EIF5A2 is positively correlated to lymphatic metastasis, the tumor invasion depth and neoplasm staging. Kaplan-Meier analysis shows that a patient overexpressed by the EIF5A2 has poor overall survival (p is less than 0.001). Multivariate analysis also proves that the EIF5A2 is an independent prognostic factor. The EIF5A2 possibly takes important effects in invasion and metastasis of esophageal squamous cell carcinoma. Further experimental data proves that overexpression of the EIF5A2 can be caused by gene amplification and oxygen deprivation; the EIF5A2 can be combined into a promoter region of HIF1a to up-regulate expression of the HIF1a; and the EIF5A2 can induce epithelial-mesenchymal transition conversion and promote angiopoiesis of the esophageal squamous cell carcinoma so as to promote invasion and metastasis of the esophageal squamous cell carcinoma. Knockout of the EIF5A2 can obviously inhibit tumor metastasis and the silent EIF5A2 is expected to be a potential target of esophageal squamous cell carcinoma treatment.

The invention belongs to the field of gene engineering, and discloses detection and an application of a novel cervical cancer metastasis marker. The cervical cancer metastasis marker is a lymphatic metastasis mode LVEM wrapped by tumor-associated macrophages, and is applied to diagnosis for distinguishing metastatic and non-metastatic early cervical cancers. Aiming at defects that an existing method for evaluating preoperative early cervical cancer lymph node metastasis is not high in sensitivity, has limitation on detection of micro-metastatic lymph nodes, is not high in timeliness and economic practicability, has false negative or false positive, is not high in sensitivity and specificity of the existing tumor marker and the like, based on a fact that an expression level of the LVEM canserve as an index for evaluating the lymph node metastasis state of a cervical cancer patient, the LVEM is developed as a marker, the expression level of the LVEM in cervical cancer tissue is detectedthrough a multicolor immunofluorescence technology, and the lymph node metastasis state of the cervical cancer patient can be more sensitively and specifically evaluated before an operation.

The invention belongs to the technical field of medical biology, and particularly relates to an ovarian cancer marker and application thereof. The invention proposes that the expression level of PRPF6 in ovarian cancer is closely related to FIGO staging and is irrelevant to age, differentiation degree and lymph node metastasis for the first time. The expression levels of the PRPF6 gene and the encoded protein thereof in the ovarian cancer drug-resistant cells/tissues are detected through PCR, immunohistochemistry and other methods, high expression of the PRPF6 in the drug-resistant cells/tissues is found, and it is clear that the PRPF6 can be used as the ovarian cancer paclitaxel drug-resistant marker. By inhibiting the expression level of the PRPF6, the drug resistance of paclitaxel can be inhibited, the invasion and migration of ovarian cancer cells can be reduced, cell apoptosis can be induced, and tumor growth can be inhibited, so that the PRPF6 inhibitor can be used as a potential target spot for the paclitaxel chemotherapy drug resistance treatment of the ovarian cancer, and a reference basis is provided for clinical diagnosis and treatment of the chemotherapy drug resistance type ovarian cancer. The method has wide application prospects and huge potential social benefits.

The invention belongs to the technical field of biological medicine, and provides a novel molecular target SF3B1 for preventing or treating breast cancer and application of the target in the parathionof drugs for preventing or treating breast cancer. The SF3B1 gene is used as a target, and the expression of the SF3B1 gene is reduced by adopting gene knockout, gene knockdown or chemical drugs. Theexpression of SF3B1 in breast cancer cells was significantly improved compared with that in normal tissue cells. SF3B1 expression level is correlated with lymph node metastasis. SF3B1 knockout in breast cancer can induce apoptosis and cell cycle arrest. SF3B1 knockout can reduce cell proliferation, colony formation, invasion and migration ability. Exon skipping is the most common splicing event after SF3B1 knockout. Researches show that SF3B1 may be an important molecular target for the treatment of breast cancer.

It is found for the first time that down-regulation is conducted in thyroid cancer tissues, down-regulation is more obvious in thyroid cancer tissues with lymph node metastasis, MAPK8IP1P2 down-regulation indicates poor prognosis of thyroid cancer patients, and overexpression of MAPK8IP1P2 can inhibit in-vivo tumorigenesis of thyroid cancer cells. Based on the new discovery, the MAPK8IP1P2 can beused for diagnosing whether a subject suffers from thyroid cancer or not, lymph node metastasis of thyroid cancer and survival prognosis, thyroid cancer tumorigenesis is inhibited through the medicinefor overexpression of the MAPK8IP1P2, and a new strategy is provided for diagnosis, prognosis and treatment of the thyroid cancer.

The invention provides a tumor lymph node distribution map generation method. When a tumor lymph node metastasis risk map is generated, the lymph node mark information in a case CT image is registeredinto a template CT image through image registration, the difference of manual registration of a doctor is avoided, the accuracy of lymph node position information during statistics is improved, the doctor can be helped to know the tumor lymph node metastasis risk more visually, and assistance is provided for the doctor to diagnose and sketch a target area. Moreover, the lymph node density function is determined by solving the uniform distribution function, a lymph node density map is obtained, the risk probability of different lymph node diseases can be obviously displayed, and a good auxiliary effect is achieved for doctors to sketch lymph nodes and lymph node partition boundaries.

The invention provides a lymph node metastasis prediction model construction and training method and device, equipment and a medium. The method comprises the steps: obtaining a plurality of transcriptome sample sequencing data or a plurality of miRNA sample sequencing data, and screening m transcriptome markers or n miRNA markers from the data; dividing the sample sequencing data into a training set and a test set according to a one-leaving cross validation method; judging whether lymph node metastasis occurs or not so as to calculate a binarized metastasis value, performing mean value removal normalization processing, establishing a partial least squares regression model and a logistic regression model, and taking a score value of the test set as a prediction result to obtain a logistic regression prediction value of the test set; and repeating M times to complete the training of the lymph node metastasis prediction model. According to the method, the expression matrix of the marker is substituted into the machine learning model, so that the lymph node metastasis can be judged, the AUC can be improved to 90% or above by utilizing two-level data of the transcriptome and miRNA, and the diagnosis efficiency is greatly improved.