27 results about "Thyroid papillary carcinoma" patented technology

The invention discloses a disease diagnosis method and system based on multi-modal space-frequency domain adaptive fusion, and relates to the field of artificial intelligence and biomedical engineering.The method comprises the steps that multi-modal data are standardized, the unified and standardized multi-modal data are coded, and multi-modal initial feature representation is obtained; after projection and gating alignment and cross-modal interactive attention alignment are carried out on the initial feature representation of each modal, enhanced representations of each modal are obtained, and then the enhanced representations of each modal are fused into a shared feature representation; performing deep feature extraction on the enhanced representation of each mode to obtain deep features of each mode, and performing adaptive multi-domain feature enhancement processing to obtain multi-domain enhanced features of each mode; performing semantic alignment on the multi-domain enhanced features of each mode, and then performing fusion through a hierarchical attention mechanism to obtain fusion features; and the fusion features are input into a diagnosis network for prediction, a disease diagnosis result is obtained, and the intelligent diagnosis precision and robustness of papillary thyroid carcinoma are improved.

The invention provides a papillary thyroid carcinoma neck lymph node metastasis risk prediction method and system based on blood indexes and TI-RADS grading, and relates to the technical field of medical data analysis. According to the method, an original data set is constructed by obtaining TI-RADS classification, the maximum diameter of nodules, the number of nodules, gender, age and conventional hematology indexes including apolipoprotein B and carcino-embryonic antigen of a patient, characteristic variables are screened by adopting LASSO regression, and an independent prediction risk factor model is established in combination with multi-factor Logistic regression. And further constructing a column graph model, carrying out performance verification through multiple statistical indexes, and deploying the model to a webpage calculator based on a shiyapp to realize convenient output of the individualized risk probability. According to the method, efficient and accurate prediction of the preoperative lymph node metastasis risk is realized, and reliable decision support can be provided for clinic.

The invention relates to the technical field of near-field imaging, in particular to a papillary thyroid carcinoma identification method based on terahertz imaging. According to the technical scheme, the method comprises the following steps that two sets of sections at the same position of the thyroid tissue of a patient are obtained, one set is stained sections, and the other set is unstained sections; and comparing the two groups of slices through an optical microscope, observing the position corresponding relation of the two groups of slices, and selecting an observation area based on cell morphological characteristics. According to the invention, synchronous acquisition of tissue apparent morphology and internal structure under nanoscale resolution is realized through the terahertz near-field imaging system, automatic analysis of an undyed thyroid section can be completed within 30 minutes by combining multi-modal feature fusion and a target detection algorithm, objective positioning and diagnosis scores of a cancerous region are directly output, and the accuracy and accuracy of diagnosis of the cancerous region are improved. And rapid, lossless and quantitative papillary thyroid carcinoma identification is realized.

The present application relates to the technical field of biological medicine, and particularly relates to application of a circPSD3 inhibitor in PTC related drugs. Knocking down of circPSD3 can significantly inhibit the proliferation, migration and invasion of PTC cells, and the circPSD3 inhibitor can prevent or treat thyroid papillary carcinoma by inhibiting circPSD3. Therefore, the circPSD3 inhibitor can be used for preparing a drug for preventing or treating thyroid papillary carcinoma.

The application discloses a method for predicting the lymph node metastasis risk of thyroid papillary carcinoma based on an integrated machine learning model. Specifically, the application provides a training method for an integrated risk prediction model for the lymph node metastasis of thyroid papillary carcinoma, which comprises the following steps: (s1) providing a data set comprising the expression data of marker genes of thyroid cancer patients with and without lymph node metastasis; (s2) training a basic model: training a basic prediction model based on the data set; (s3) training a fusion layer: training a stacked ensemble model and a bagging ensemble model based on the output results of the basic prediction model; (s4) training a decision layer: training a weighted fusion model based on the output results of the stacked ensemble model and the bagging ensemble model, thereby obtaining the integrated risk prediction model. The model can realize accurate prediction of the lymph node metastasis risk of thyroid papillary carcinoma.

The application relates to the technical field of cardiovascular internal medicine disease automation, in particular to a cardiovascular internal medicine disease onset risk prediction method and system. The application can effectively evaluate and predict the cardiovascular internal medicine disease, especially the coronary heart disease, by jointly using multiple groups of clinical indexes and multiple image group feature data, the score data is more intuitive to determine the onset degree of the thyroid papillary carcinoma, so that the coronary heart disease onset risk can be accurately judged. Compared with the blood vessel CT angiography technology in the prior art, the application embodiment combines the image group feature data in the ultrasonic image with the clinical indexes, so that the discrimination result is more accurate.

This application provides a YOLOv11-based multimodal detection system and method for papillary thyroid carcinoma cells, relating to the field of image detection technology. It addresses the problem in existing technologies of achieving both high accuracy and robustness in papillary thyroid carcinoma cell detection under limited computing power. The system specifically includes: an improved backbone network that extracts first-modal features from images at different scales by introducing C3k2_Faster and C2MSLA modules; a priori pyramid module for STEM processing and progressive downsampling of the image, and outputs second-modal features aligned with the first-modal features at different scales through convolutional projection; a gated fusion module for channel-level weighted fusion of the first and second-modal features at corresponding scales, outputting fused features; a neck module for transferring and aggregating the fused features; and a head module for outputting the target detection results. This application is used for detecting papillary thyroid carcinoma cells.

The invention discloses a protein marker combination for predicting papillary thyroid carcinoma lateral cervical lymph node metastasis and a screening method and application thereof, and belongs to the technical field of biological medicine. The marker combination comprises 31 proteins, namely VWA8, PDHX, DENR, ATP5MG, SFTPB, MAOA, PHB1, CHI3L1, ACAA2, PTPN9, AFM, ACADVL, HSPE1, PPP2R2A, REEP5, FABP5, NME3, AUH, TMEM214, NDUFAF2, PHB2, FUCA2, PAXX, APOO, TMEM109, CHID1, MAGT1, ARL8B, BCAP29, AFG3L2 and MTCH2, in total. According to the method, multiple independent proteomics queues are integrated, direction consistency and performance screening are combined, a high-stability candidate marker library is constructed, a prediction model is constructed based on machine learning, and excellent prediction performance is shown in multiple verification sets. The method can be used for evaluating the preoperative lateral cervical lymph node metastasis risk of papillary thyroid carcinoma, and has an important clinical transformation value.

The application discloses a thyroid papillary carcinoma pathological image classification method based on multi-task learning, realizes multi-task learning on high cell type tumor cell rotation target detection, cell nucleus target detection and cell nucleus classification, and further takes the abnormal evaluation of the high cell type tumor cell detection and the abnormal evaluation of the cell nucleus detection as two auxiliary tasks. The application effectively overcomes the problem of insufficient single task information utilization, improves the accuracy and efficiency of the classification and / or statistics of the thyroid papillary carcinoma pathological image through the information mutual assistance among the multi-tasks.

This invention relates to the field of medical auxiliary diagnosis, specifically disclosing an interpretable machine learning model for predicting papillary thyroid carcinoma. The model includes collecting clinical data and related examination data of patients with papillary thyroid carcinoma to construct an initial feature dataset; performing initial feature screening using clinical significance testing, and determining key features based on Lasso regression and 10-fold cross-validation; constructing a diagnostic model for papillary thyroid carcinoma based on machine learning algorithms, inputting the key features into the diagnostic model for training, and selecting the optimal model; and using the SHAP method to perform interpretability analysis on the optimal model to determine the most critical features affecting the model. The predictive model constructed in this invention can integrate a large amount of diverse clinical data, significantly improving the accuracy of the predictive model, thereby providing accurate and reliable auxiliary diagnosis for the treatment of patients with papillary thyroid carcinoma.

The application discloses application of an alkaloid compound in dog tooth flower and belongs to the technical field of antitumor. The alkaloid compound has a structural formula as shown in the specification, can be extracted and separated from medicinal dog tooth flower of a plant of the dog tooth flower genus in the Apocynaceae family, can induce tumor cell apoptosis by inhibiting cell activity and cell proliferation, and has certain medical uses in resisting tumors such as human renal clear cell carcinoma and papillary thyroid carcinoma.

The invention discloses a methylation marker for identifying papillary thyroid carcinoma invasion subtype, a diagnosis model and application. According to the application, methylation sequencing data analysis is carried out on the basis of measured tissue samples of papillary thyroid carcinoma invasion subtypes and papillary thyroid carcinoma non-invasion subtypes, markers for identifying the papillary thyroid carcinoma invasion subtypes are identified, and a corresponding diagnosis model is constructed on the basis of the markers; based on the marker and / or the diagnosis model, whether papillary thyroid carcinoma invasion subtypes exist or not can be effectively identified, the defect that the papillary thyroid carcinoma invasion subtypes cannot be distinguished through an existing identification method is overcome, and a new method is provided for identification of the papillary thyroid carcinoma invasion subtypes; the detection process based on the marker or the diagnosis model is high in safety, and large-scale clinical application is facilitated.

The invention provides a method and system for evaluating the papillary thyroid carcinoma risk of a thyroid nodule patient, and relates to the technical field of medical information processing and tumor risk evaluation. According to the method, a postoperative pathological result, TI-RADS classification and multiple laboratory inspection indexes are collected to construct a data set, variables are screened through minimum absolute contraction and selection operator regression, TI-RADS 4b, TI-RADS 4c, GLU, ALB, FN and CEA are determined as independent risk factors based on Logistic regression, and a joint prediction model is established. And further converting a model regression coefficient into a total integral and constructing a column graph model, and finally deploying a visual risk prediction calculator to realize quantitative evaluation of the individual PTC risk. According to the invention, the risk discrimination accuracy of the intermediate graded thyroid nodules is improved.

The invention discloses a marker, a kit and a method for thyroid papillary carcinoma lymphatic metastasis assessment, and belongs to the technical field of carbohydrate chemistry. The marker comprises a miRNA (micro Ribonucleic Acid) biomarker and an IgG (Immunoglobulin G) N-glycan, wherein the miRNA biomarkers are miR-616-3p and miR-1285-5p, and the miRNA biomarkers are miR-616-3p and miR-1285- And the IgG N-glycans are GP4, GP10, GP13 and GP24. A biomarker model is constructed by jointly detecting six key indexes of miR-616-3p, miR-1285-5p, GP4, GP10, GP13 and GP24, the problem of multicollinearity is effectively solved, the AUC value reaches 0.930, the general efficiency level of a clinical conventional diagnosis method is remarkably exceeded, and a high-precision judgment tool is provided for PTC LNM clinical decision. The numerical value shows extremely high discrimination capability; and the constructed model is based on internal correlation analysis of miRNA and initial glycan which are remarkably related to PTC LNM, and has good specificity and reliability.

The invention relates to a papillary thyroid carcinoma risk assessment system and device and a medium, and the system comprises an obtaining module which is used for obtaining a first significant predictive factor and a second significant predictive factor of a user; the diagnosis module is used for inputting the first significant predictive factor of the user into a papillary thyroid carcinoma diagnosis column diagram prediction model to obtain the papillary thyroid carcinoma suffering risk of the user; and the recurrence risk prediction module is used for inputting the second significant prediction factor of the user into a recurrence risk column diagram prediction model to obtain the initial recurrence risk of the papillary thyroid carcinoma of the user. According to the invention, PTC diagnosis and recurrence risk prediction can be carried out in a non-invasive, quantifiable and efficient manner.

This application relates to the field of otolaryngology technology, specifically a method and system for predicting the risk of papillary thyroid carcinoma. By combining multiple sets of clinical indicators and multiple imaging feature data, this application can effectively assess and predict the risk of papillary thyroid carcinoma. The scoring data provides a more intuitive determination of the severity of papillary thyroid carcinoma, thereby enabling the differentiation between atypical subacute thyroiditis and papillary thyroid carcinoma. Compared to existing technologies, the discrimination results of the embodiments in this application are more accurate.

The present application belongs to the technical field of medical image analysis, and particularly relates to a thyroid cell pathology image auxiliary analysis system. The system of the present application comprises an input module for inputting a thyroid cell pathology section image; a cell detection module for detecting a target cell through a neural network model; a semantic classification module for performing semantic classification on the target cell to obtain a classification label; and a knowledge graph search module for searching in a knowledge graph according to the classification label and performing textual interpretation on an obtained diagnosis result. The system of the present application can perform high-accuracy auxiliary diagnosis on thyroid papillary carcinoma. Meanwhile, the diagnosis result can provide a diagnosis basis and reference literature according to the knowledge graph, so that the AI auxiliary pathology diagnosis has public credibility. Therefore, the present application has a good application prospect.

The application relates to the technical field of thyroid papillary carcinoma classification, and discloses a multi-source thyroid papillary carcinoma classification system based on federal learning, which comprises a central server and a plurality of local devices connected with the central server; the local device is used for acquiring a thyroid ultrasound image and classifying the thyroid ultrasound image by adopting a classification model; the central server and the plurality of local devices are used for updating the classification model by federal learning based on a training set; wherein the global model in the federal learning process is updated based on the data points in the training set adopted by each local device and the local models uploaded by each local device. The accuracy of thyroid papillary carcinoma classification is improved.

The invention relates to the technical field of terahertz near-field imaging, in particular to a thyroid papillary carcinoma cell terahertz near-field imaging quality distinguishing method. According to the technical scheme, the method comprises the following steps: placing an unstained papillary thyroid cancer cell sample under a terahertz near-field imaging system; a plurality of to-be-detected areas on the sample are selected to be scanned, terahertz imaging pictures of all the areas are obtained, and terahertz feedback voltage signals in the scanning process are synchronously recorded. The terahertz feedback voltage is used as an objective criterion, the subjectivity and blindness problems of detection position selection are solved, a high-quality imaging area can be quickly screened out, and therefore the detection efficiency and the instrument use efficiency are remarkably improved; the terahertz image obtained based on the method is higher in signal-to-noise ratio and feature significance, the accuracy and reliability of cancer cell recognition are enhanced, and the method does not need to modify hardware, is simple and convenient to operate, and is easy to integrate and popularize in an existing system.

The invention discloses a noninvasive prediction system and method for thyroid cancer gene mutation. The method comprises the following steps: collecting preoperative enhanced CT (Computed Tomography) image data, clinical data and BRAFV600E gene mutation detection results of papillary thyroid carcinoma patients; preprocessing the CT image, delineating a region of interest and extracting image omics features; optimal radiomics features are obtained through feature screening; constructing a radiomics prediction model by using a machine learning algorithm based on the optimal radiomics characteristics; constructing a clinical prediction model in combination with the clinical risk factors; and fusing the two models to construct a joint prediction model, and analyzing and evaluating the performance of the model through a subject working characteristic curve and a decision curve. The method realizes preoperative noninvasive prediction of papillary thyroid carcinoma BRAFV600E gene mutation state, has high accuracy and clinical application value, and can provide auxiliary support for individualized treatment decision.

The invention discloses an immune-related early screening marker for predicting and diagnosing radioiodine treatment effect response after total resection of papillary thyroid carcinoma based on Olink proteomics as well as a selection method and application of the immune-related early screening marker. A serum sample before radioiodine treatment after total resection of a papillary thyroid carcinoma patient is measured; up-regulated protein HGF in a group with poor iodine treatment effect is screened out, the reliability of the up-regulated protein HGF for predicting the radioactive iodine treatment effect is verified on the basis of an independent queue, and it is found that serum psTg and serum HGF are independent predictive factors of disease-free lifetime. The HGF protein screened by the invention can be used for evaluating the curative effect of radioactive iodine treatment and providing a target spot for mechanism research, and meanwhile, the protein can be used for preparing a kit which is poor in iodine treatment effect and is used for screening before radioactive iodine treatment.

The application belongs to the technical field of bioinformatics, and discloses a PTC risk stratification evaluation model and application. The model takes biomarker expression levels as input variables, and the biomarkers include BDKRB1, CXCL9, GP1BA, GPR132, ITGA5, KCNMB2, LPAR1, MEFV, MEP1A, MXD1, OPRK1, PDE4B, PROK2, RTP4, SERPINE1 and TNFSF15. The model integrates gene expression data, statistical models and clinical verification, combines gene expression with tumor immune microenvironment and drug sensitivity, realizes multi-dimensional risk evaluation, accurately evaluates the prognosis risk of patients with thyroid papillary carcinoma, and provides a basis for clinical individualized treatment.

The invention relates to a thyroid cancer side neck lymph node metastasis prediction model construction method and application. The thyroid cancer side neck lymph node metastasis prediction model comprises a Logistic regression model and a decision process module. The Logistic regression model is used for calculating an actual risk value based on a value of a primary tumor maximum diameter, a value of a tumor boundary, a value of a BRAF V600E mutation state, a value of micro-calcification existence, a value of an aspect ratio and a value of single / double-side cancerous lesion; the decision process module is used for giving a decision suggestion according to the calculated actual risk value and a set decision process; the model provides a new quantitative tool for preoperative evaluation of papillary thyroid carcinoma patients, can provide individualized and precise treatment schemes for clinic, reduces unnecessary treatment and missed diagnosis, and finally improves the treatment effect and life quality of the patients.

The invention discloses application of a NOD1 gene and an MYBBP1A gene as targets in screening candidate drugs for inhibiting or relieving papillary thyroid carcinoma (PTC) lymph node metastasis, application of the NOD1 gene and the MYBBP1A gene as markers in preparing products for evaluating the risk of PTC lymph node metastasis, a method for screening the candidate drugs and a kit for screening. Belongs to the technical field of biological medicine. Aiming at the problem that at present, the PTC lymph node metastasis is lack of effective predictive biomarkers and therapeutic targets, the invention reveals for the first time that the NOD1 gene can regulate and control the BCL2 / BAX pathway by up-regulating the MYBBP1A gene expression so as to enhance the anoikal apoptosis sensitivity of PTC cells, thereby inhibiting the lymph node metastasis. On the basis, the gene can be used as a target for drug screening and a marker for risk assessment, the screening method and the kit can be used for discovering potential treatment drugs, and a new tool is provided for accurate diagnosis and treatment of PTC.

The invention provides a lymph node metastasis prediction method and system for a papillary thyroid carcinoma patient, and relates to the technical field of data processing, and the method comprises the steps: building an ultrasonic image data set of the papillary thyroid carcinoma patient; determining a tumor region-of-interest image including a peritumor region in each ultrasonic image; extracting comprehensive features of the tumor region-of-interest image; screening a plurality of significant features related to the diffusion degree label from the comprehensive features in combination with information entropy, and carrying out correlation normalization scoring on each significant feature and the diffusion degree label; adjusting the feature weight of the corresponding significant feature in a pre-trained convolutional neural network model according to the correlation normalization score; acquiring a current ultrasonic image of a papillary thyroid carcinoma patient to be predicted; and inputting the current ultrasonic image into the adjusted pre-trained convolutional neural network model, and outputting a predicted diffusion degree corresponding to the papillary thyroid carcinoma patient to be predicted.

The invention discloses a product for efficiently detecting whether a papillary thyroid carcinoma patient suffers from lymph node metastasis or not and application of the product, and the content of TG and TSHR mRNA in the lymph node of the papillary thyroid carcinoma patient is detected by detecting the expression quantity of TG and TSHR genes in the neck lymph node and utilizing a fluorescent quantitative PCR technology. And whether the papillary thyroid cancer has lymph node metastasis can be well predicted. The invention also discloses a primer combination, a reagent / kit / product for detecting the expression quantity of the TG and TSHR genes in the cervical lymph node, and application of the primer combination, the reagent / kit / product. The method has a wide application prospect in detecting whether the thyroid cancer is subjected to cervical lymph node metastasis or not.

The present application relates to the technical field of diagnosis and risk assessment of thyroid papillary carcinoma, and particularly relates to a composition, application and system for preoperative diagnosis and / or risk assessment of thyroid papillary carcinoma. The composition for preoperative diagnosis and / or risk assessment of thyroid papillary carcinoma comprises reagents for measuring the expression level of CLDN16 protein and / or the mRNA expression level of the gene encoding CLDN16 protein. Through the composition, the mRNA expression level of CLDN16 in thyroid tissue can be detected preoperatively, which is used for accurate diagnosis of the primary lesion and metastatic lesion of thyroid papillary carcinoma, and simultaneously, the disease risk of thyroid papillary carcinoma is accurately predicted to guide clinical decision-making.