85 results about "Recurrence risk" patented technology

The invention relates to the technical field of medical data analysis, in particular to a brain tumor curative effect analysis system which comprises a tumor data sensing layer for collecting multi-department diagnosis and treatment data, tumor image data and patient pathology monitoring data; the tumor feature processing center extracts data features, correlates data and core features before and after treatment through an attention mechanism, and generates a tumor complete-cycle unified feature map; the therapeutic effect dynamic analysis unit evaluates the therapeutic effect in stages, and outputs a therapeutic effect index and a recurrence risk value through a self-supervised model; the dynamic adaptation decision module is used for generating personalized treatment adjustment suggestions based on the dynamic change of the blood brain barrier in combination with the curative effect index, the recurrence risk value and the multi-omics characteristics of the patient; and the AI multi-department consultation unit automatically matches similar cases with field expert suggestions, and formulates a target diagnosis and treatment scheme based on a visual platform and multi-department doctor collaborative consultation in combination with personalized treatment adjustment suggestions. Therefore, the problems of lagging effect evaluation, insufficient diagnosis and treatment suggestions and the like in the prior art are solved.

The invention discloses a system and a method for predicting postoperative recurrence risk after triple negative breast cancer neoadjuvant therapy based on multi-modal time sequence medical image data, and belongs to the field of medical image analysis. The system comprises a data processing module used for constructing a multi-modal data set; the multi-modal feature extraction and screening module is used for extracting deep learning, radiomics and tumor habitat features from the region and carrying out feature screening; the model training module is used for constructing a time sequence model based on a Transform architecture and carrying out training through a multi-task learning strategy integrated with time consistency constraint and gene association auxiliary loss; and the recurrence risk prediction module is used for loading the trained model and outputting a recurrence probability and a risk level. According to the method, the multi-modal time sequence image and gene information are fused, so that the recurrence risk of the triple negative breast cancer patient is dynamically and accurately quantified, and support is provided for clinical individualized treatment decision.

The invention provides a breast cancer recurrence risk prediction method, system and device based on an ultrasonic image, and relates to the field of intelligent medical treatment, the method uses a deep convolutional neural network to perform deep network feature extraction on a breast ultrasonic image, and uses a deep learning semantic segmentation algorithm to perform accurate positioning and automatic segmentation on a breast tumor region of interest, thereby improving the accuracy of breast cancer recurrence risk prediction. Meanwhile, habitat analysis is carried out on the ultrasonic images to extract tumor heterogeneity features, multi-level and multi-mode features such as deep learning features, radiomics features and habitat analysis features are fused, a breast cancer recurrence risk prediction model is constructed, breast cancer recurrence risk prediction is carried out, and a breast cancer recurrence risk assessment result is output. And a quantitative basis is provided for clinical treatment decisions. The accuracy and robustness of recurrence risk prediction are remarkably improved through multi-feature fusion, and standardization and objectification of breast cancer prognosis evaluation are achieved. In addition, the method further has the advantages of being easy and convenient to operate, low in cost, noninvasive, nonradiative, good in repeatability and the like.

The invention discloses a breast cancer recurrence risk prediction method and system based on multi-modal data missing interpolation and gene interpretability enhancement. The method comprises the following steps: firstly, dynamically generating and complementing features of a missing mode by matching a generative adversarial network with a mode missing mask matrix; then, a feature screening mechanism driven by gene information is introduced, through a multi-task learning network, image feature extraction is supervised by using a gene expression tag in a model training process, and image features highly associated with recurrence-related genes are screened out; and finally, fusing the complemented multi-modal time sequence characteristics by adopting Transform, and outputting a recurrence risk probability. According to the method, the robust prediction performance can be realized under the condition of data missing, and meanwhile, image interpretation with a molecular biology basis is provided for the feature screening process of the model, so that the reliability and clinical acceptability of the whole system are enhanced.

The invention provides a coronary heart disease recurrence risk assessment method and device, equipment and a storage medium, and relates to the technical field of medical data processing. The method comprises the following steps: acquiring dynamic behavior data, physiological data and static risk indexes of a target patient; calculating a treatment compliance index and a rehabilitation health index of the target patient based on the dynamic behavior data and the physiological data of the target patient; and inputting the treatment compliance index, the rehabilitation health index and the static risk index into a trained coronary heart disease recurrence risk scoring model to obtain a coronary heart disease recurrence risk score of the target patient. According to the method, objective and quantitative recurrence risk scores can be obtained, more accurate decision support is provided for clinicians, and early warning and personalized intervention can be realized, so that the prognosis of patients is improved, and the medical cost is reduced.

The invention discloses a model uncertainty-driven man-machine collaborative risk grading interpretation method, system and device and a computer readable storage medium. According to the method, under federated learning deployment, calibration confidence, bucket-level calibration deviation and multi-model inconsistency are simultaneously calculated for a single sample, and a comprehensive uncertainty score is formed to perform risk grading: when the comprehensive uncertainty score exceeds a threshold value or the calibration confidence is insufficient, manual re-checking is automatically triggered; otherwise, directly outputting the AI result. Artificially confirmed samples enter a feedback sample library for subsequent federation retraining, temperature parameters and barrel counting are periodically updated, and a continuous learning closed loop is constructed. According to the scheme, in medical scenes such as lung CT nodule detection and lung cancer I-stage recurrence risk prediction, the diagnosis efficiency and clinical safety are effectively considered, and the long-term stability and credibility of the model are improved.

The invention discloses a depression recurrence risk intelligent early warning method, system and device based on multi-modal data and artificial intelligence, and relates to the field of depression classification early warning, and the method comprises the steps: carrying out the individualized deviation calculation based on the baseline features and multi-modal brain image features of a target patient, obtaining an individual multi-modal brain image deviation feature vector; dimension reduction processing is carried out on the individualized multi-mode brain image deviation feature vector, the genetic features and the environment and clinical features, the individualized multi-mode brain image deviation feature vector, the genetic features and the environment and clinical features are input into a pre-trained layered integrated classification model and a pre-trained layered integrated risk early warning model, and depression subtype classification tags and risk probabilities are obtained; in the pre-training process of the hierarchical integration classification model and the hierarchical integration risk early warning model, multi-modal feature fusion and hierarchical integration learning strategies are adopted, and samples from a plurality of data centers are used for model training and verification. According to the method, the accuracy and individualization degree of classification and early warning are improved, and the generalization ability and robustness of the model are also improved.

The invention provides a mental disorder aided decision-making method and system based on multi-modal data, and belongs to the technical field of disease aided decision-making, the method is applied to a system comprising a data acquisition module, a preliminary screening module and an aided decision-making module, and the method specifically comprises the following steps: preprocessing the multi-modal data of a patient; in combination with the mental disorder risk level of the patient of the preliminary screening model, decision assistance is triggered according to the mental disorder risk level, or corresponding decision suggestions are matched and output; when decision assistance is triggered, the disease classification probability and severity are obtained through a diagnosis model based on a cross-modal attention mechanism, meanwhile, according to a time-dependent risk prediction model, a survival probability curve of a recurrence risk is generated in combination with historical diagnosis data of a patient, and decision assistance suggestions are determined by integrating outputs of the two models. According to the method, on the basis of multi-modal data, multiple types of intelligent models are fused, objective data support is provided in the assessment and intervention process, and the missed diagnosis and misdiagnosis risks of mental disorders are reduced.

The invention discloses a rectal cancer postoperative recurrence risk prediction system and method based on multi-modal time sequence data, and relates to the technical field of medical artificial intelligence. The system comprises a data acquisition and preprocessing module, a feature extraction module and a multi-modal feature fusion and modeling module. The method comprises the following steps: constructing a cross-modal data set containing time sequence clinical data, a time sequence MR image and a biopsy digital pathological image; respectively extracting clinical features, radiomics and deep learning features of the MR image, and nucleus morphology and spatial distribution features of the pathological image; and fusing all the features by using a Transform network, and constructing a prediction model. According to the method, macroscopic images, micropathology and dynamic time sequence information are integrated, tumor heterogeneity is comprehensively quantified, the problem that prediction of a single-mode static model is not accurate is solved, the postoperative recurrence risk of the stage III rectal cancer patient can be evaluated more accurately, and clinical treatment decision making is assisted.

The invention discloses a sugar chain marker combination for predicting the recurrence risk of a gastric cancer patient after treatment and application of the sugar chain marker combination. The invention discovers that the levels of six specific N-sugar chains (NGA2F, NG1A2F, NA3, NA3Fb, NA4 and NA4Fb) in blood are obviously related to relapse during definite diagnosis of gastric cancer for the first time. On the basis, a gastric cancer recurrence risk prediction model GC-GPSS is constructed through Cox regression. According to the model, individual risk scores are calculated by using a quantification formula containing a fixed regression coefficient (beta), and patients are divided into a high-risk group and a low-risk group according to a preset threshold. A verification result shows that the model can effectively distinguish patient groups with different recurrence risks. The marker combination, the prediction model and the system provided by the invention provide a brand new tool for realizing earlier and more objective recurrence risk assessment in the early stage of gastric cancer diagnosis and treatment, and have important clinical application value.

This invention relates to the field of medical technology, specifically to a method for preoperative risk assessment and prediction in liver transplant patients with hepatocellular carcinoma, comprising the following steps: Sample collection: selecting plasma samples and corresponding clinicopathological information from liver transplant recipients of hepatocellular carcinoma, and clarifying the inclusion and exclusion criteria for samples; Plasma cell-free DNA extraction and whole-genome sequencing: extracting and quality-controlling cell-free DNA from the plasma samples collected in step S1, constructing a sequencing library, and performing low-coverage whole-genome sequencing. This invention utilizes plasma-extracted cfDNA for whole-genome sequencing, combined with clinical testing information, to construct a preoperative risk assessment and prediction model for postoperative recurrence in liver transplant recipients of hepatocellular carcinoma based on non-invasive testing. This model can be used to predict the probability of recurrence-free survival before liver transplantation. The model derivation cohort integrates clinical records and circulating tumor DNA data for preoperative recurrence risk prediction.

The application belongs to the field of biomedicine, and particularly relates to application of CRYL1 protein in preparation of products for evaluating, diagnosing or assisting in diagnosing postoperative recurrence risk of calcium oxalate kidney stone combined with renal papillary calcium plaque, and a sequence of the CRYL1 protein is shown as SEQ ID NO. 1. The application firstly finds that expression of CRYL1 protein in renal tubular and collecting duct cells of renal papillary calcium plaque tissue is reduced, and it is proved through experiments that urine CRYL1 protein is a postoperative recurrence predictor and prediction marker of patients with CaOx kidney stone combined with renal papillary calcium plaque, and a CRYL1 protein detection kit is further developed for detecting or evaluating postoperative recurrence risk of patients with CaOx kidney stone combined with renal papillary calcium plaque, which promotes personalized follow-up and prevention scheme of the patients, and has great application prospect in the clinic.

The invention belongs to the field of myocardial infarction diagnosis and research, and particularly relates to a serum lipid biomarker for predicting the recurrence risk of myocardial infarction and application of the serum lipid biomarker. The invention discloses a serum lipid biomarker for predicting the recurrence risk of myocardial infarction. The serum lipid biomarker for predicting the recurrence risk of myocardial infarction is PI (18: 2), PI (16: 0), TG (20: 2), PC (22: 4) and PI (22: 6). According to the method, through lipid deconstruction analysis with higher resolution, lipid molecules of a specific chain structure closely related to the PRMI risk can be identified, and more accurate prediction of the recurrence risk is realized. The deconstructed lipid molecular marker provided by the invention has higher specificity and reliability in clinical application, not only can make up for the defects of the traditional lipid marker, but also provides a brand new technical means and application prospect for early recognition and individualized intervention of AMI postoperative recurrence risk.

The invention discloses an atrial fibrillation recurrence prediction method based on artificial intelligence, and belongs to the technical field of medical information, and the method specifically comprises the steps: inputting a discrete clinical event record after an ablation operation of a target patient, and carrying out the inversion of a continuous internal state evolution path from the discrete clinical event record through an event-driven hidden state deduction model. The path is divided into a plurality of recovery stages and a feature vector is generated. And taking the last stage as a query object, retrieving similar historical stages in the pre-constructed group recovery process graph, and extracting a complete stage chain of the similar historical stages until a clear outcome. And mapping back to a physiological state space, and forming a plurality of candidate future evolution chains starting from the current state of the patient through coordinate translation. And finally, calculating the likelihood score of each candidate chain in combination with the historical event mode of the patient, and outputting a personalized recurrence risk prediction path set after sorting and screening. The invention provides a new approach for dynamically predicting the recurrence risk of the atrial fibrillation with both individual adaptability and time sequence interpretation.

A lymphoma recurrence risk prediction method, device and equipment based on MRD are disclosed, comprising: acquiring clinical feature information related to diffuse large B-cell lymphoma; in response to the clinical feature information, calculating a plurality of baseline clinical features through a structured constraint target Bayesian network model to obtain an initial recurrence risk probability of diffuse large B-cell lymphoma of a target object; the structure constraint is used to prohibit direct connection between each baseline clinical feature; according to the initial recurrence risk probability, the state of minimal residual disease related to diffuse large B-cell lymphoma and high-risk pathological factors, the multidimensional calculation of recurrence risk is carried out through the target random forest model to obtain the final recurrence risk probability of the target object; according to the final recurrence risk probability, the recurrence risk information of diffuse large B-cell lymphoma of the target object is generated. To improve the interpretability and accuracy of lymphoma recurrence risk prediction.

The application provides a laryngeal squamous cell carcinoma prognosis gene methylation marker and application thereof, and relates to the technical field of clinical medicine. The methylation marker is CORO1C and MAPK11, and a recurrence risk prediction model is constructed based on the two sites. The prediction model is independent of factors such as stage, age and differentiation of patients, proving the independence and universality of the prediction model. Through the RRBS technology, the methylation changes of the genes can be comprehensively analyzed at high resolution, and the prognosis value of the markers in laryngeal squamous cell carcinoma is verified. Compared with traditional single clinical pathological indicators, the methylation marker based on the molecular level provided by the application has high accuracy and sensitivity, and can provide more accurate basis for the recurrence prediction of laryngeal squamous cell carcinoma.

The invention provides a vascular embolism recurrence risk prediction method and device and electronic equipment. The vascular embolism recurrence risk prediction method comprises the steps that multi-modal data of a patient at each time point is acquired, the multi-modal data of each time point comprises at least two modal data of a vascular image, a medical text, biochemical test information and a physiological signal, and the multi-modal data of at least one time point comprises the vascular image; determining a first feature and a second feature according to the multi-modal data of each time point, the first feature being obtained by analyzing correlation between the modal data and reflecting a recurrence risk level of the patient at the current time point, and the second feature being obtained by analyzing a change rule of the multi-modal data along with time and reflecting a recurrence risk evolution trend of the patient; the vascular embolism recurrence risk of the patient in the future period is predicted according to the first feature and the second feature, and the prediction accuracy of the vascular embolism recurrence risk can be improved.

The application provides a gout recurrence risk assessment method and system based on a neutrophil-to-lymphocyte ratio, comprising: data acquisition, data preprocessing, and generating gout recurrence risk assessment sample data through data standardization processing; establishing a joint model of a Cox proportional hazards regression model and a competing risk model to evaluate the correlation between the neutrophil-to-lymphocyte ratio (NLR) and gout recurrence; adding NLR as a characteristic variable of a prognosis factor of gout recurrence risk to a baseline model to construct multiple gout recurrence risk candidate prediction models; screening to obtain a target gout recurrence risk assessment model; generating an evaluation result; and visual display. The method can effectively handle the problems of incomplete and skewed distribution of clinical data, improve the quality and stability of the data, improve the accuracy of evaluation and prediction by screening out an effective target gout recurrence risk assessment model, and provide reliable auxiliary decision support for clinicians.

The present application relates to the technical field of rheumatism and immunity disease management, and particularly relates to a remote intelligent management method and system for rheumatism and immunity patients. Clinical indexes, environmental monitoring and life behavior data are acquired to construct a multi-element characteristic vector, which is input into a deep learning network to obtain a disease activity prediction result; the prediction result and the characteristic vector are input into a recurrence risk assessment network containing a collaborative constraint layer, and a consistency correction is performed based on a medical prior constraint to obtain a risk assessment result; a counterfactual replacement is performed on the characteristic vector through a causal inference algorithm, the risk assessment network is input to obtain a counterfactual prediction value, a difference value is calculated as a causal contribution degree, risk driving factors are screened, and quantitative intervention suggestions are generated; and operable early warning information is generated based on the driving factors and the intervention suggestions. The present application improves the accuracy of recurrence risk prediction and the pertinence of intervention suggestions.

Provided herein include new antibodies reactive for canine CD3, which are shown to substantially increase activation of canine T cells; new multi-specific immune cell engager molecules based on the canine CD3 antibodies, which are shown to effectively bind canine cancer antigens and recruit T cells for killing of the cancer cells; as well as new recombinant proteins derived from canine cartilage protein fragments and hydrogels thereof. Uses of these compositions are also provided, which include therapeutic uses of antibodies and multi-specific immune cell engager molecules for treatment of cancers or other diseases in dogs, as well as uses of hydrogels for local immunotherapy delivery for reduction of post-surgical recurrence risk, reduction of cancer at surgically inoperable sites, provision of palliation, and / or substitution for surgery.

In alternative embodiments, an immunohistochemical (IHC) method is provided for reproducibly determining and scoring the degree of expression of protein sealant protein 18.2 in a tissue sample. In alternative embodiments, methods are provided for diagnosing, treating or ameliorating or assessing the risk of recurrence of cancer or tumors using the IHC methods as provided herein. In alternative embodiments, kits comprising components and instructions for practicing the methods as provided herein are provided. Described herein are methods for scoring sealin 18.2 expression and using the score as a companion or supplemental diagnosis or treatment or amelioration of cancer or tumor.

FIELD: clinical gastroenterology.SUBSTANCE: intended to predict the risk of relapse of autoimmune hepatitis after discontinuation of immunosuppressive therapy. The patient undergoes a clinical and biochemical examination and the relapse risk probability index is determined using the formula: PI RR = –0.394×(IGA≥ 9) + 1.252×(AT) + 0.915×(a-SLA / LP) + 0.555×(a-LKM1) – 0.692×(IgG norm) + 0.316×(obesity), where PI RR is the prognostic index of recurrence risk; HAI is the histological activity index of more than 9 according to Knodell (binary indicator: HAI ≥ 9 corresponds to the multiplier “1”; HAI < 9 corresponds to the multiplier “0”); AB – the presence of autoantibodies (binary indicator: detection of at least 1 corresponds to the multiplier “1”; absence of autoantibodies corresponds to the multiplier “0”); a-SLA / LP – antibodies to soluble liver / kidney antigen (binary indicator: presence – corresponds to the multiplier “1”; absence – corresponds to the multiplier “0”); a-LKM1 – antibodies to liver and pancreas microsomes (binary indicator: presence corresponds to the multiplier “1”; absence corresponds to the multiplier “0”); IgG – immunoglobulin G (binary indicator: normal Ig G level corresponds to the multiplier “1”; elevated IgG level corresponds to the multiplier “0”); obesity (BMI ≥ 30) – (binary indicator: presence of BMI ≥ 30 corresponds to a multiplier of “1”; BMI < 30 corresponds to the multiplier “0”). With the value of PI RR < 0.93 – low probability of relapse, PI RR > 0.93 – high probability of relapse.EFFECT: increased accuracy in predicting the risk of recurrence of autoimmune hepatitis after discontinuation of immunosuppressive therapy.1 cl, 2 ex

This invention discloses a system for predicting the risk of recurrence after lumbar disc herniation surgery based on domain offset correction, relating to the fields of medical data processing and clinical disease risk prediction technology. The system acquires multimodal clinical and imaging feature vectors and follow-up outcome data from training and independent validation cohorts. It trains a center classifier to quantify and correct for differences in multi-center data distribution, calculates and normalizes the importance weights of each training case, trains a survival analysis base learner based on the processed weights, and performs stacking and ensemble integration. The final deployment model is determined by combining the independent validation case cohort. The final deployment model is then used to infer the risk of recurrence in target patients after lumbar disc herniation surgery, outputting individualized recurrence risk scores, risk stratification, and recurrence-free survival curves. This improves the robustness and reliability of the risk prediction system in cross-center scenarios and is suitable for follow-up management and clinical decision support after lumbar disc herniation surgery.

The present application relates to the technical field of urinary calculus risk assessment, and particularly relates to a kind of upper urinary tract calculus postoperative recurrence risk assessment system based on multi-modal data.The present application trains neural network according to the training stone state in patient body and previous examination vector, determines the expected comprehensive load index of verification patient and the expected local load index under each mode using trained neural network, and obtains the prediction contribution weight of each mode;Using prediction contribution weight to adjust the expected local load index of all modes of the patient to be tested during follow-up, obtain the initial recurrence risk degree, and combine the life habits similarity and disease characteristics similarity of the patient to be tested and historical recurrence patients, obtain the calculus recurrence risk degree;Based on calculus recurrence risk degree, the recurrence risk of upper urinary tract calculus of the patient to be tested after operation is evaluated.The present application combines the static basic risk and dynamic disease risk of patient, reduces the influence of multi-modal data loss during follow-up on recurrence risk assessment.

The application discloses a stroke prediction method and device based on a cerebrovascular image feature group, a medium and a product, relates to the field of image processing, and comprises the following steps: constructing a clinical database; constructing a clinical cause classification prediction model according to multi-modal image feature group data, clinical feature data and patient clinical cause classification; determining cerebrovascular image features by adopting a cerebrovascular tissue segmentation model and voxel-based morphological analysis according to TOF-MRA, and performing positioning diagnosis on a responsible blood vessel area according to the cerebrovascular image features; and constructing a stroke recurrence risk prediction model according to the cerebrovascular image features in the TOF-MRA, SWI, T1WI, T2-FLAIR and corresponding clinical feature data. The application can quickly and accurately realize cause classification of an acute stroke patient in a clinical scene, accurately identify a responsible blood vessel, and realize recurrence risk prediction in an early stage of the disease.

The invention provides a marker detection kit for typing or prognosis evaluation after liver cancer thermal ablation, a detection analysis system and application of the marker detection kit and the detection analysis system. In order to solve the clinical problems that after thermal ablation treatment, hepatocellular carcinoma is prone to relapse and the mechanism is unknown, in a clinical sample and an orthotopic xenograft model derived from a patient, it is jointly confirmed that a remarkable DNA hypermethylation phenomenon exists in residual and relapsed HCC tissue after ablation, and the phenomenon is accompanied by remarkable up-regulation of DNMT1; therefore, heat stress can trigger and promote an epigenetic-metabolic cascade reaction of tumors by activating a DNA hypermethylation 5mC mechanism. On the basis, it is clear that DNMT1-mediated DNA hypermethylated 5mC is one of important mechanisms of HCC recurrence after thermal ablation, an accurate detection marker is provided for recognizing the recurrence risk, and a detection and analysis system is established to improve the layered diagnosis capacity after liver cancer thermal ablation, so that the prognosis and survival conditions of patients are improved.

The present application relates to a kind of reagent for evaluating the risk of recurrence of epithelial ovarian cancer, belong to molecular biology technical field.The use of the present application is specifically the use of reagent for specifically detecting the expression level of SNORD18C and / or SNORD84 in the surgical tissue sample of epithelial ovarian cancer in the preparation of kit for evaluating the risk of recurrence of epithelial ovarian cancer patient after resection.The present application finds the change of SNORD18C and SNORD84 expression in the surgical tissue sample of epithelial ovarian cancer, and the change of the expression is closely related to the risk of recurrence of epithelial ovarian cancer patient after resection.Therefore, by detecting the expression of SNORD18C and / or SNORD84 in the tissue sample of epithelial ovarian cancer, and combining two binomial logistic regression model, the risk of recurrence of epithelial ovarian cancer patient after resection is evaluated, with higher sensitivity and specificity.

The application discloses a lung adenocarcinoma recurrence prediction method and system based on multi-omics data analysis, relates to the technical field of precision medicine, and comprises the following steps: collecting folate metabolism group data, a transcription group expression spectrum and methylation level data of a target gene promoter region of tumor tissue of a lung adenocarcinoma patient; constructing a metabolism-epigenetic correlation topology graph based on a spatial adjacent relationship, screening a significant causal relationship between methylation variation and metabolism fluctuation through causal analysis, and generating a methylation metabolism significant causal edge set; fusing simulation metabolism channel characteristics and the methylation metabolism significant causal edge set, constructing a lung adenocarcinoma recurrence risk prediction model, triggering a high-risk early warning signal through time sequence analysis of risk factor fluctuation; through the construction of the metabolism-epigenetic correlation topology graph and the screening of the significant causal edge set, the causal correlation modeling of multi-omics data in the spatial dimension is realized, the robustness of the recurrence prediction model is improved, the prediction performance is synergistically enhanced, and the accuracy of lung adenocarcinoma recurrence prediction is significantly improved.

The application discloses a rectal cancer postoperative recurrence risk prediction system and method based on multi-modal time series data, and relates to the technical field of medical artificial intelligence. The system comprises a data acquisition and preprocessing module, a feature extraction module and a multi-modal feature fusion and modeling module. The method comprises the following steps: constructing a cross-modal data set comprising time series clinical data, time series MR images and biopsy digital pathology images; extracting clinical features, imageomics and deep learning features of MR images, and cell nucleus morphology and spatial distribution features of pathology images respectively; and fusing all the features by using a Transform network to construct a prediction model. The application integrates macroscopic images, microscopic pathology and dynamic time series information, comprehensively quantifies tumor heterogeneity, solves the problem of inaccurate prediction of a single modal static model, and can more accurately evaluate the postoperative recurrence risk of a stage III rectal cancer patient, thereby assisting clinical treatment decision-making.

The application discloses a triple negative breast cancer post-neoadjuvant therapy postoperative recurrence risk prediction system and method based on multi-modal time sequence medical image data, and belongs to the medical image analysis field.The system comprises: a data processing module for constructing a multi-modal data set; a multi-modal feature extraction and screening module for extracting deep learning, imageomics and tumor habitat features from the region, and performing feature screening; a model training module for constructing a time sequence model based on a Transformer architecture, and training through a multi-task learning strategy of integrating time consistency constraints and gene association auxiliary loss; and a recurrence risk prediction module for loading the trained model, and outputting a recurrence probability and a risk level.The application realizes dynamic and accurate quantification of the recurrence risk of triple negative breast cancer patients by fusing multi-modal time sequence images and gene information, and provides support for clinical individualized treatment decisions.