49 results about "Disease Screening" patented technology

The invention discloses a disease risk assessment method and screening device based on a multi-group student physical collaborative digital network, and relates to the field of intelligent medical detection. In order to solve the defect that multi-omics-level system collaborative analysis and robust risk assessment are difficult to realize in the prior art, the technical scheme provided by the invention is as follows: acquiring a plasma sample, acquiring a spectral signal by adopting an attenuated total reflection Fourier transform infrared spectrum, and establishing a plasma spectrum digital information space; the method comprises the following steps: constructing a biological collaborative digital network containing four nodes of protein, lipid, saccharides and nucleic acid based on pathophysiology priori knowledge, and defining node strength, edge weight and network collaborative efficiency; a health baseline configuration file is established by using a health sample, a standardized deviation score of a to-be-tested sample is calculated, a comprehensive risk score is obtained, a disease screening result is output in combination with a machine learning model, and digital evaluation of multi-omics collaborative characteristics is realized. The method is suitable for non-invasive rapid screening and risk assessment work of neurodegenerative diseases and mental diseases.

A rapid diagnostic device for detecting multiple biomarkers in bodily fluid samples, particularly useful for disease screening including breast cancer. The device comprises a housing containing at least one test strip with a sample receiving zone, conjugate pad, and multiple test zones. The test strip utilizes specific materials including Cytiva GF / DVA and Ahlstrom 1667 sample pads, an Ahlstrom 6613 conjugate pad with carboxylated 150 nm gold nanoshell conjugates, and a Sartorius CN140 membrane with precisely positioned test and control zones. The device simultaneously detects multiple biomarkers, such as hCG and CA-15-3, using specific antibodies. Features include a built-in safety lancet, integrated buffer system, and compatibility with various sample types. Results are available within ten minutes, with options for quantitative analysis via a dedicated reader or smartphone application. This multi-biomarker approach potentially improves screening accuracy compared to single-marker tests, offering versatility for detecting various medical conditions.

The application discloses a kind of children's rare lung disease multi-modal intelligent screening method, system and equipment, belong to medical artificial intelligence technical field.The method includes: obtaining the medical image data, clinical text data and corresponding visit time information generated by the children at multiple time points, and the multi-modal data is standardized;Based on the multi-modal time series data after processing, construct cross-modal time series logic diagram, the cross-modal time series logic diagram is used to represent the association between different modal data and its evolution characteristics with time change;The cross-modal time series logic diagram is input into the children's rare lung disease screening model for analysis, and the risk prediction result of suffering from rare lung disease is output.The screening model includes multi-modal feature extraction module, cross-modal feature fusion module and global comprehensive prediction module, by the joint modeling of image feature, text feature and time series information, realize the intelligent screening of children's rare lung disease.The application can overcome the problem of multi-modal information fragmentation and insufficient use of time series association in the prior art, and is suitable for the auxiliary screening and risk assessment scene of children's rare lung disease.

The invention provides a multi-modal fusion-based congenital disease early screening method and device, and the method comprises the steps: collecting a target case ultrasonic image and a case report, building a cue word template, and guiding a large language model to output a structured text; extracting visual semantic description based on a Q-former architecture, obtaining image features and enhanced text features, fusing the image features and the enhanced text features to obtain joint features, inputting the joint features to a pre-trained classifier to obtain a disease prediction result, and establishing a total loss function optimization classifier; and for a plurality of ultrasonic images of a single case, outputting a final disease prediction result by adopting a majority voting strategy so as to realize early screening of congenital diseases. According to the method, image features are subjected to semantic supplementation by introducing migration knowledge and text information of a large language model, a deep interaction mechanism of an image modal and a text modal is constructed, the problem of alignment of different-source modal data is solved, effective fusion of cross-modal deep features is realized, and thus the accuracy and reliability of disease screening are remarkably improved.

The application relates to the technical field of medical treatment and discloses a liver chronic disease screening method, a device and a storage medium.The method comprises the following steps: a liver detection system collects liver stiffness data and liver fat attenuation parameters of a target object; a mobile terminal system receives the liver stiffness data and the liver fat attenuation parameters, combines the liver stiffness data and the liver fat attenuation parameters with basic information of a preset target object, generates acquisition characteristic data, carries out label marking matrix processing on pretreatment integrated data of the cloud service system, generates a label marking matrix, carries out fitting residual processing on the label marking matrix, obtains extended decision tree data, carries out discrete sampling processing on the extended decision tree data, obtains a sparse vector, carries out classification calculation processing on the sparse vector, obtains a classification result, and generates a disease screening report based on the classification result.In the embodiment of the application, through system architecture and cloud service system data processing, the early warning timeliness and accuracy of liver chronic disease screening are improved.

The application provides a FFA image generation system, method, medium and device based on a dual-domain constraint Mamba diffusion model, which integrates dual spatial and frequency domain constraints for cross-modal generation of FFA images from CFP images. Through a learnable wavelet feature extractor, the key frequency components of blood vessels are effectively extracted from the fundus CFP image, enhancing the structured guidance of the vascular edge representation in the generated FFA image. In the spatial domain, through a dual-pyramid feature extractor, the local details and global semantics of the fundus lesion area are effectively fused, improving the consistency of the lesion representation in the generated FFA image. The dual-domain conditional Mamba module serves as the denoising core, effectively coordinating spatial and frequency information to improve the clarity and accuracy of the image. The application is verified on the Hajeb, MPOS and clinical data sets, with PSNR reaching 30.11 and 29.40, effectively generating high-quality FFA images that retain vascular details, providing a new method for retinal disease screening.

The application discloses a kind of X-ray film lung disease screening systems of fusing multi-level features, including lung parenchyma segmentation module, lung disease preliminary screening module, multi-level feature construction module, lung disease screening module;Lung parenchyma segmentation module is used to obtain lung parenchyma part from complete chest X-ray film segmentation;Lung disease preliminary screening module is used to construct based on feature consistency variation auto-encoding generation adversarial network and train it, and obtains preliminary screening abnormal score using trained generation adversarial network;Multi-level feature construction module is used to extract features of different semantic levels, including the extraction of bottom visual features, middle layer depth features and high layer experience features;Lung disease screening module is used to construct lung disease screening model using multi-level features and the abnormal score obtained by lung disease preliminary screening module, and obtains the final lung disease classification result.The present application can effectively solve the problem that current computer-aided lung disease screening field research is difficult to be applied to practical clinical scene.

The application discloses an application of a prostate hyperplasia related marker in preparation of a product for detecting prostate hyperplasia, and the prostate hyperplasia related marker is at least one selected from MINP1, ACTBL and APOC4 proteins. In the technical scheme, MINP1, ACTBL and APOC4 are combined as a detection marker for prostate hyperplasia (BPH), so that the complementarity of the three in different stages of diseases can be fully exerted, and the comprehensive performance of the detection product is obviously improved. MINP1 and ACTBL participate in disease progression by regulating prostate cell proliferation and apoptosis, and APOC4 can present significant expression changes in blood cells of early BPH patients, so that BPH disease screening can be accurately performed. When the three are applied in cooperation, early screening of BPH can be realized, and the activity and severity of the lesion can be evaluated, so that a detection system covering the whole process of disease occurrence and development is formed, the limitation of a single marker in the diagnosis dimension is effectively made up, and the comprehensiveness and accuracy of BPH detection are greatly improved.

The invention relates to the technical field of feature selection and mode recognition, in particular to a special child disease screening method based on multi-granularity particle ball hypergraph feature selection. According to the method, single-granularity information is converted into multi-granularity knowledge expression, and a particle-ball hypergraph is constructed by using a complex association relationship between features so as to select features most favorable for screening diseases of special children, so that the generalization ability and the discrimination ability of a model are enhanced; meanwhile, the SVM classifier based on the optimal feature subspace is constructed to achieve screening of the special child diseases, and the screening accuracy of the special child diseases is improved; the method can more effectively adapt to the feature difference of different data sets, optimize the feature subspace, and improve the accuracy and calculation efficiency of special child disease screening.

The application provides a non-target detection device and system based on a nanopore and a detection method thereof, the non-target detection device and system based on a nanopore are used for non-target detection of a complex matrix through a nanopore, feature extraction is performed on a nanopore detection graph, and sample classification is realized through model construction, the detection method does not make a prior definition on a to-be-detected target, and various molecular information existing in serum is acquired in a net catching manner, non-target capture and overall state analysis of various molecules in serum are realized, and a new way of rapid and portable disease screening is provided.The application breaks through the limitation of traditional single marker detection by combining the nanopore technology and machine learning, and is expected to promote the development of precision medicine in a more efficient and comprehensive direction.

The application discloses a kind of based on visual guidance's mechanical arm mouthwash nursing, breath detection and holographic diagnosis and treatment auxiliary system and method, it is related to stomatology field, including: main control module, auxiliary mechanical arm module, gas detection module, visual sensing module, diagnosis and treatment intelligent body interaction module, audio and video acquisition communication module with main control module electricity connection, and multi-modal mobile nursing terminal.The application realizes the pose control of mechanical arm and the imaging visual angle adjustment of diagnosis and treatment intelligent body by visual sensing system, integrates supine position automatic mouthwash nursing, exhalation component disease screening, doctor-patient / holographic visualization communication, full-process audio and video diagnosis and treatment support, non-standard oral speech driven standard medical record automatic generation, automatically collects non-standard oral speech content in diagnosis and treatment full process, generates standardization medical record meeting medical quality control requirement, greatly improves diagnosis and treatment efficiency, patient comfort and diagnosis and treatment standardization, and can be widely integrated in dental treatment chair.

The application discloses a kind of multi-disease prediction systems based on binocular fundus image, including fundus feature extraction module, similarity-difference feature fusion module, clinical feature extraction module, multi-modal feature fusion module and multi-disease classification prediction module.System uses unified backbone network to extract left and right fundus image features, by similarity-difference feature fusion module, the features of two-way are added to each element to obtain preliminary fusion features, and the absolute value is obtained by subtracting each element to obtain different features, after normalization and 1 complement operation generates dissimilarity weight and similarity weight, separate out dissimilarity information and similarity information after weighting fusion according to hyperparameter α Fusion fundus feature is obtained;Multi-dimensional clinical variable features are extracted by two fully connected layers, after fundus features and clinical features are spliced, input multi-disease classification prediction module, and output disease prevalence probability.The application makes full use of the correlation and complementarity of binocular fundus image, and realizes high-precision, low-cost multi-disease screening combined with clinical indicators.

The invention relates to the technical field of data processing, and discloses a mild cognitive impairment detection system based on multi-level data, and the system comprises a terminal device which is used for collecting physiological monitoring data, clinical narrative data and multi-modal test data of a user; the data processing module is used for performing interference identification and information purification on the multi-modal test data to generate a purified cognitive response matrix; the cognitive evaluation module is used for performing cognitive ability decoupling and group benchmarking based on the purified cognitive response matrix and outputting an individual ability level; and the closed-loop management module is used for constructing a longitudinal decline slope model based on a score sequence of individual historical multiple evaluations and carrying out risk early warning and intervention recommendation. According to the method, passive disease screening of cognitive health management is converted into an active, personalized and continuous risk monitoring and intervention process, and a powerful technical tool is provided for delaying cognitive decline.

The invention provides a diabetic foot data inspection and early screening method and system based on an AI model. Belongs to the technical field of disease screening. The method comprises the steps that diabetic foot data of a patient are collected in real time through multi-modal data collection equipment, and the collected diabetic foot data are transmitted into an edge computing network to be processed; the processed diabetic foot data are transmitted into a cloud space, a multi-modal AI model is constructed through a convolutional neural network, and key features are extracted from the diabetic foot data based on the multi-modal AI model. The edge computing network can reduce cloud burden and accelerate data processing speed by processing data, and cloud computing is responsible for training and optimization of a deep learning model, so that advanced analysis of data is realized, and prediction precision is improved.

The invention provides an anterior segment transmission interference microscopic imaging device, method and system, and relates to the technical field of medical optical imaging and ophthalmic diagnosis. The single-frame imaging field of view is not less than 2mm * 1mm and is larger than that of a common clinical confocal microscope and a corneal endothelial mirror, so that the statistical reliability and the lesion detection rate can be improved; through a transmission interference mechanism, corneal nerves, epithelial cells and crystalline lens fine structures can be displayed in a high contrast manner, and the method is particularly suitable for low-scattering transparent tissues; a common-path optical structure is adopted, a reference arm or a high-speed scanning unit is not needed, and the system is small in size, low in cost and good in stability; in the examination process, contact with the ocular surface or introduction of a contrast agent is not needed, and discomfort and risks possibly caused by traditional contact type or intrusive type examination are avoided; the method can be used for corneal nerve evaluation, endothelial disease screening, crystalline lens microstructure observation and preoperative / postoperative follow-up visit.

The application provides an explainable coronary heart disease noninvasive screening method and system based on multi-agent decision, and the method comprises the following steps: encoding according to a preset field order based on noninvasive health assessment data to obtain an input vector, inputting the input vector into a grade score prediction model, outputting a score vector of each candidate risk grade, and selecting the grade corresponding to the maximum score vector as a target risk grade. Evidence description information is constructed according to the source information of the noninvasive health assessment data and the related information of the target risk grade, and the evidence description information is divided into multiple evidence units according to different data types. It is judged whether each evidence unit has the ability to support the target risk grade, and the evidence unit judgment result is obtained, and each evidence unit corresponds to a stability weight. The establishment judgment result is calculated according to the evidence unit judgment result, the stability weight and the establishment threshold, and it is judged whether the target risk grade is established at the evidence level according to the establishment judgment result, and the reliability of disease screening is improved.

The application discloses a neurodegenerative disease screening method based on medical image segmentation. First, the original brain MRI image is preprocessed, unified into a standard template space, and the maximum transverse cross section is found for training the image segmentation model. Then, under the condition of a small sample case, the image segmentation model is used to realize accurate segmentation of the brain MRI image, and then the neurodegenerative disease screening of different indexes is completed.

This invention discloses an early Parkinson's disease screening method based on olfactory evoked EEG signals. It constructs a dual-channel, cross-dimensional feature fusion framework through multimodal basic feature extraction, cross-channel feature association modeling, and adaptive feature space expansion. Before inputting features into the classification model, the feature vectors are standardized and normalized to eliminate the influence of differences in dimensions and numerical ranges among different features. Finally, an attention weight mechanism is introduced, and the processed feature vectors are input into a pre-trained classification model to output the classification result of early Parkinson's disease risk. This invention also discloses an early Parkinson's disease screening system based on olfactory evoked EEG signals. Through olfactory stimulation paradigms, low-guided cross-dimensional feature fusion dimensionality enhancement, and standardized data processing, this invention constructs a sensitive, objective, and efficient early Parkinson's disease screening model, effectively solving the problems of diagnostic lag, strong subjectivity, and single feature in existing technologies.

The invention provides an expiration metabolite-based Parkinson's disease screening model construction method, a screening method and related equipment, and the method comprises the steps: obtaining an expiration sample of a target user, carrying out the metabolite detection, constructing a model training data set, calculating the importance of each metabolic feature based on a random forest classification model, and carrying out the screening of a Parkinson's disease. Selecting first N features according to the importance sequence, constructing a target feature subset, dividing metabolites in the target feature subset into an up-regulation type metabolite set and a down-regulation type metabolite set, and constructing a quantitative scoring model based on the relative relationship of the two sets; and then calculating an expiration metabolite score of the target user, generating a screening result according to the expiration metabolite score and a preset discrimination condition, and determining whether the target user is positive or negative of the Parkinson's disease. According to the method, an efficient, non-invasive and rapid solution can be provided for early screening of Parkinson's disease, the automatic screening process can be achieved, and the screening efficiency and accuracy are improved.

The invention provides an ultrasonic image detection method based on deep learning, and the method comprises the steps: obtaining a to-be-detected fetal ultrasonic image; image segmentation processing and image enhancement processing are carried out on the ultrasonic image, the image segmentation processing is used for extracting a symbolic anatomical structure which at least contains a fetal head area and is related to the to-be-detected chromosome disease, and the image enhancement processing at least comprises image noise reduction and feature contrast improvement; the ultrasonic image obtained through processing is detected through a pre-trained image detection model, a risk result for the to-be-detected chromosome disease is output, and the image detection model adopts a hybrid architecture combining a residual neural network with an attention mechanism. According to the method, the conversion of fetal chromosome disease screening from subjective experience to objective intelligent analysis is realized through the end-to-end deep learning model, and the screening accuracy, robustness and consistency are remarkably improved.

The invention belongs to the technical field of artificial intelligence and medical image analysis, and particularly relates to a full-slide image target detection method based on deep learning and a tumor detection system applying the method. The method comprises the following steps: preprocessing a full-slide image to obtain a patch-level image; constructing a single-stage target detection model by taking patch-level tumor images as input and taking classification and regression results of lesion tumors as output; lS convolution is introduced to simulate size seeing and focusing, so that the tumor detection efficiency is improved; the improved GD multi-scale fusion module is used for collecting and distributing cross-level information in the C2f multi-scale feature fusion network; and outputting a detection result of the diseased tumor in the patch-level tumor image. The lesion tumor can be automatically, efficiently and accurately detected from the full-slide image, and a contribution is made to disease screening.

This invention discloses a Parkinson's disease assessment method and detection wristband based on aerial spiral drawing, relating to the field of Parkinson's disease screening technology. The key technical points include the following steps: outputting pre-set assessment task guidance information to the user to guide the user in completing pre-set action sequences for initial calibration, static holding tasks, and aerial drawing tasks; collecting raw motion signals of the user's hand while the user executes the pre-set action sequences according to the guidance information, and recording the start and end time markers for each task; segmenting the time-series motion data sequence according to the start and end time markers to obtain task motion data sub-sequences corresponding to the pre-set assessment tasks; inputting the task motion data sub-sequences into a pre-set assessment model to obtain a motion abnormality risk score; and generating a Parkinson's disease risk assessment result based on the motion abnormality risk score. The effect is to provide data support for monitoring the course of Parkinson's disease and evaluating treatment efficacy.

The invention belongs to the technical field of disease screening, and particularly relates to an ear-nose-throat disease intelligent screening system and method based on multi-modal data, and the method comprises the steps: constructing an ear-nose-throat anatomical parameterized model according to a clinical image, and generating a virtual image; extracting interpretable anatomical features according to the mixed image data set, mapping the interpretable anatomical features to an ear-nose-throat disease knowledge graph, and establishing a diagnosis association rule through predicate logical reasoning; the method comprises the following steps: reading pixel features of a clinical image, matching a map rule, iterating a closed loop through a manual correction rule, and converting diagnosis adjustment into map rule supplementation; constructing a federal rule sharing framework, uploading rule correction parameters, and aggregating results through a federal average algorithm; and designing a hierarchical screening process according to the diagnosis rule model, and pushing high-confidence positive cases to superior hospitals to form a screening system. According to the invention, on the basis of virtual-real fusion data construction, a highly-adaptive and universal ear-nose-throat disease intelligent screening system is constructed through symbolized logical reasoning and federal rule sharing.

The invention provides a live pig leg and foot disease screening and early warning method based on gait analysis and weight estimation, and relates to the technical field of livestock breeding intelligent monitoring, and the method comprises the steps: collecting side video data and depth image data when a pig walks in a preset channel; estimating the current weight of the pig according to the mapping relation between the body size parameter and the weight; frame-by-frame analysis is carried out on the side video data, a gait anomaly index is constructed, and the gait anomaly index is a quantized value of the deviation degree of the current gait feature parameters and the standard gait parameter library of the healthy pigs with the same weight. According to the method, the weight of the pig is estimated in real time through the depth image data, and the correlation model of the weight and the gait parameters is established. When it is judged that the gait is abnormal, the current gait parameter is compared with the standard gait parameter of the healthy pig with the same weight, interference of weight difference on gait judgment is effectively eliminated, and the false alarm rate is remarkably reduced.

The invention discloses a child face multi-disease screening method and system oriented to category imbalance, and the method comprises the steps: synchronously obtaining global feature representation and local feature representation of a face through multi-scale feature extraction, and carrying out the deep fusion of the global feature representation and the local feature representation, so as to comprehensively represent a complex phenotype; and finally, generating a screening result through a decision rule adaptive to long-tail distribution. The problem that the recognition result is low in accuracy when the child genetic disease is recognized is solved. According to the method, high-precision identification of various similar genetic syndromes is realized through multi-scale feature extraction under a unified framework, and the ability of identifying rare and rare disease categories of samples is remarkably improved through decision rules adapted to long-tail data distribution, so that the effect of improving the accuracy of screening multiple diseases on the face of children is achieved.

According to the non-targeted detection device and system based on the nanopore and the detection method of the non-targeted detection device and system based on the nanopore, non-targeted detection is conducted on a complex matrix through the nanopore, feature extraction is conducted on a nanopore detection map, sample classification is achieved by building a model, and according to the detection method, a to-be-detected target is not defined in advance; and various molecular information in the serum is obtained by a capturing net method, so that non-targeted capturing and overall state analysis of various molecules in the serum are realized, and a new rapid and portable way is provided for disease screening. By combining the nanopore technology and machine learning, the limitation of traditional single marker detection is broken through, and precise medical treatment is expected to be promoted to develop towards a more efficient and comprehensive direction.

The application discloses a medical image classification method and system based on multi-scale space state modeling, which comprises the following steps: firstly, dividing the input medical image into multiple non-overlapping image blocks, and mapping to the feature space through a learnable linear projection layer to obtain an initial feature map; then, using a multi-layer stacked MS-SMamba block to extract features layer by layer, wherein each MS-SMamba block comprises a main branch, an auxiliary branch, a dynamic gating fusion network, a residual connection unit and a feedforward network, realizing long-range dependence relationship capture and multi-scale feature fusion; finally, processing the output feature map of the last layer through a global feature aggregation and classification module, generating a global feature vector and outputting a classification result. The application improves the capture ability of complex pathological features in medical images, improves the calculation efficiency and clinical applicability, and is suitable for disease screening, auxiliary decision-making and other scenes in medical image diagnosis.

The invention relates to a method for accurately analyzing whole genome sequencing data copy number variation, and belongs to the technical field of biological information analysis and genome data processing. The method comprises the following steps: constructing a target interval file based on a 1kb window and exon annotation information; performing quality control, comparison and duplicate removal on the sequencing data to generate a comparison file; calculating and standardizing the target interval sequencing depth under different quality thresholds, and establishing a multi-sample depth baseline; through comparison with a base line, identifying a candidate copy number variation region in combination with a difference multiple and Z-score; and further extracting abnormal comparison information of the candidate region, judging the position of the breaking point and evaluating the credibility of variation. According to the method, the comparison interference of homologous regions is remarkably reduced, the detection resolution and the fracture point positioning precision are improved, and the method can be widely applied to the scenes of genetic disease screening, tumor variation detection and the like.

The invention relates to a prediction system for an early Parkinson's disease. The prediction system is characterized by comprising a task issuing module, a data acquisition module and a data analysis module, wherein the task issuing module issues a test task instruction to a user at the front end of the equipment; the data acquisition module is used for acquiring measurement parameters of specified behaviors through acquisition equipment according to different test tasks; and the data analysis module is used for carrying out statistics and analysis on measurement parameters based on the prediction model and carrying out early Parkinson's disease prediction. The optimal screening tool for the early Parkinson's disease is deduced on the basis of cooperation of multi-modal acquisition equipment and a prediction system for the early Parkinson's disease, early screening of the Parkinson's disease is achieved, and the clinical problem that early diagnosis of the Parkinson's disease is difficult is solved.

The application discloses a kind of platinum supported cerium-based nanoscale enzyme and its preparation and application, the nanoscale enzyme includes cerium oxide nanorod carrier and the Pt active component loaded on its surface, the Pt active component is dispersed in the form of single atom or nanocluster on the surface of cerium oxide nanorod, the surface of cerium oxide nanorod has oxygen defect, by first loading platinum monolayer on the surface of cerium dioxide nanorod, then by reduction treatment, platinum atom forms platinum nanocluster on the surface of cerium dioxide and obtains.The nanoscale enzyme of the application effectively adjusts the oxygen vacancy and Pt site on the surface of cerium dioxide, has good peroxidase-like characteristics, can be used to construct TMB colorimetric system for colorimetric analysis of thiol reducing substances, and further used for disease screening, significantly improves the distinguishing effect.