720 results about "Medical diagnostic" patented technology

The invention discloses a medical diagnosis intelligent decision-making system based on multi-modal data fusion, and the system comprises the steps: obtaining a medical image, biological features and electronic medical record data of a patient through a patient information collection unit, and extracting feature vectors from different modal data through a feature processing unit; the core of the system is a modal fusion engine, and the module combines a deep neural network and a Bayesian inference engine to realize deep learning and probability-dependent modeling of an association relationship between features; carrying out weight optimization on different modal features by adopting an attention mechanism through a self-adaptive feature optimizer, and generating optimized feature representation; the intelligent diagnosis analysis unit calculates the diagnosis probability based on the optimized features, performs auxiliary diagnosis in combination with a case knowledge base when the confidence coefficient is insufficient, and outputs a diagnosis report containing diagnosis categories, basis and suggestions; according to the method, multi-source heterogeneous data are fused, deep learning and probabilistic reasoning are combined, intelligent medical auxiliary diagnosis is achieved, and diagnosis accuracy and interpretability are improved.

The invention discloses a medical visual question-answering method and system based on multi-task modeling, and the method comprises the steps: carrying out the feature extraction of a to-be-analyzed medical image through a visual encoder, obtaining an image feature, inputting a preliminary question instruction and historical question-answering data into a dialogue large model to generate a question instruction, and obtaining a text feature through a text encoder; carrying out feature fusion on the obtained text features and image features, and carrying out self-attention image importance weighting processing and image-text alignment to obtain image-text fusion representation; and inputting a multi-target output projection layer, carrying out multi-task prediction, outputting question answers, image categories and important region masks, inputting the question answers and the image categories into a dialogue large model, and finally generating diagnosis opinions with detailed description in combination with dialogue context and multi-round interaction data and in combination with the important region masks. According to the invention, the interaction experience and the performance of the question and answer system are improved, and more accurate medical diagnosis in multi-modal complex information is facilitated.

The invention discloses a deep interpretable skin disease identification method based on small sample learning, which belongs to the field of image processing, and comprises the following steps of: respectively inputting similar or heterogeneous skin disease images into a double-branch small sample contrast learning network, segmenting a lesion area of the skin disease image to generate lesion segmentation masks, extracting shape information in the lesion segmentation masks, and identifying the shape information of the lesion segmentation masks; positioning a minimum square frame containing a lesion area, and performing clipping and zooming to obtain a lesion image; extracting the depth features of the branches corresponding to the lesion images of the two branches, calculating the contrast loss of the depth features of the double branches to optimize network parameters, and extracting multi-scale texture information at the same time; metadata containing shape information and texture information and depth features of an image are subjected to multi-modal fusion for skin disease identification, and through combination of a multi-stage deep learning network and medical diagnosis logic, features such as form and texture of a lesion area are extracted and fused step by step. The classification accuracy of skin disease identification and the interpretability of the model are improved.

A handheld medical diagnostic device integrates at least seven sensor modules, including a high-magnification camera, otoscope camera, stethoscope, infrared thermometer, EKG, pulse oximeter, body composition monitor, glucometer, and / or hematology analyzer. The device features a system-on-chip (SoC) processor for intelligent data management, edge computing, and cloud-based AI processing, while applying privacy-preserving techniques. A wireless transceiver enables data transmission and reception between the sensors, edge compute nodes, and cloud platforms. The ergonomically designed housing includes a display with a force-sensitive layer for user input and navigation. The high-magnification camera module offers 300× magnification for visualizing blood cells and skin, with an annular LED array, encryption engine, and physically unclonable function (PUF) circuit. The otoscope camera module features a narrow profile for ear, nose, and throat imaging, with an annular LED array.

The invention provides a medical diagnosis system based on chain reasoning and multi-modal fusion and application thereof, and belongs to the technical field of medical care informatics. The system comprises a data preprocessing module, a data fusion module, a model reasoning module and an output module, and can perform deep processing and intelligent analysis on multi-modal medical data (including text data, medical image data and structured data) of a patient. And the output module provides a diagnosis result and a detailed reasoning process, so that the interpretability and the credibility of the diagnosis result are improved. Through multi-modal data fusion, a chained reasoning mechanism and optimized loss function design, the accuracy, generalization ability and interpretability of disease diagnosis are remarkably improved, the limitation of the traditional technology in the aspects of single-modal analysis and black box reasoning is broken through, transparent, efficient and intelligent diagnosis decision support is provided for clinicians, and the clinical application prospect is wide. And intelligent and precise development of medical diagnosis is promoted.

The invention relates to the technical field of medical diagnosis, in particular to a dysphagia detection and automatic scoring system based on a high-resolution acoustic sensor. Comprising a three-dimensional curved surface type acoustic sensing array module, a self-adaptive environment noise compensation module, a swallowing stage dynamic segmentation module, a multi-dimensional feature extraction engine, a swallowing abnormal mode classifier and a dynamic weight scoring model. A self-adaptive environment noise compensation module, a time-frequency domain feature extraction module and a dynamic weight scoring model are combined, the swallowing process is monitored and scored in real time, the system automatically identifies and analyzes acoustic features of an oral cavity preparation period, a pharyngeal period and an esophageal period, and through multi-dimensional feature fusion, dynamic weighting and neural network optimization, the swallowing process is monitored and scored in real time. The method has the advantages of being non-invasive, easy and convenient to operate, high in real-time performance and the like, and can be widely applied to early screening, evaluation and follow-up visit of clinical dysphagia.

Devices, systems, methods, and software for providing remote medical diagnosis and therapy to a subject comprising: a module for conducting telecommunications with a telemedicalist; a module for applying a diagnostic or a therapeutic analysis; an apparatus for dispensing one or more medical items from an inventory of medical items, the inventory of medical items risk profiled to a subject, a population, a venue, or a situation; and optionally, a biosensor apparatus.

The invention provides a preparation method of an electrochemical biosensor based on a PLL-coated VPAu modified nuclear track membrane, and belongs to the field of electrochemical biosensing analysis. The electrochemical biosensor for detecting troponin is constructed by adsorbing a PLL (at) VPAu composite nanomaterial synthesized by an ultrasonic liquid phase assisted method into a nuclear track membrane pore channel through electrostatic interaction and connecting a specific recognition molecule of a target to the surface of the pore channel modified by the PLL (at) VPAu by utilizing a bonding reaction mechanism. After a target object is captured by the recognition molecules connected to the nuclear track membrane, the effective aperture of the nuclear track membrane nanopores is reduced, and the electrochemical workstation can convert the biological behavior into an electric signal, so that high-sensitivity and rapid detection of the target protein is realized. The method has very important theoretical and practical significance in the field of medical diagnosis, and a new direction is provided for application of the nuclear track membrane in the field of analysis and detection.

The invention relates to the technical field of medical information analysis, in particular to a breast cancer disease science popularization method and system based on a multi-modal knowledge graph. The method comprises the following steps: acquiring and processing breast cancer image samples and text data; breast cancer specific features are extracted from the breast cancer image sample; in a knowledge graph, creating corresponding nodes for the breast cancer specific characteristics, and establishing a mapping relation with medical diagnosis information to form multi-modal unified representation; associating medical text entities in the text data with breast cancer specific feature nodes to form a multi-modal knowledge graph; and obtaining to-be-diagnosed information input by a user, retrieving the associated nodes related to the to-be-diagnosed information from the multi-modal knowledge graph, and outputting popular science content. According to the application, individuation, authority and interactivity of breast cancer science popularization can be realized, and high-quality science popularization service is provided for patients and the public.

The invention belongs to the field of artificial intelligence and fundus image enhancement, and discloses a fundus image enhancement method and system based on machine learning, electronic equipment and a storage medium, and the method comprises the steps: obtaining an original fundus spectral image, and carrying out the preprocessing of the original fundus spectral image, and obtaining a preprocessed spectral image; constructing a backbone network based on a residual network, and extracting multi-scale features of the preprocessed spectral image in combination with cavity convolution; introducing a channel-space-spectrum multi-attention module into the backbone network, and performing multi-attention fusion on the multi-scale features to obtain an enhanced feature map; and performing adversarial training on the backbone network by using the generative adversarial network and the enhanced feature map, and performing image enhancement on the collected fundus spectral image by using the trained network to obtain an enhanced fundus spectral image. According to the method, more-dimensional image support is provided for medical diagnosis, the quality of the fundus image can be effectively improved, the diagnosis accuracy of a doctor on fundus lesions is improved, and the method has important clinical application value.

The invention discloses a small sample medical image classification method, system and device and a storage medium, and belongs to the field of medical image processing and artificial intelligence. The method comprises the following steps: segmenting an input medical image into an overlapped slice sequence with spatial context information through a semantic sequence construction module; extracting the feature representation of each slice and adding a position code; processing the feature sequence through a sequence enhancement module, and capturing a long-distance dependency relationship; constructing a category prototype considering feature distribution by using a distribution perception prototype calculation module; and calculating the distance between the query sample and each type of prototype by using the mahalanobis distance, and performing classification decision. According to an end-to-end architecture specially designed for Mamba characteristics, the fundamental problem that a traditional few-sample learning method is insufficient in adaptability in the field of medical images is solved in a breakthrough mode, and an efficient and robust technical path with practical value is provided for a medical diagnosis auxiliary system.

The invention discloses a skin image super-resolution conversion system and a skin image super-resolution conversion method based on deep learning, and relates to the technical field of image super-resolution conversion, and the system evaluates whether illumination is qualified or not by collecting skin near-illumination and analyzing illumination conditions of the skin near-illumination, establishing a light environment analysis model and calculating a light influence coefficient. The method comprises the following steps: preprocessing qualified images, including color space conversion, histogram equalization, edge detection and denoising; thirdly, evaluating the quality of image pixels, calculating a plurality of pixel features, judging whether the pixel features conform to the standard or not, and performing optimization through strategies such as sharpening and de-noising; a multi-scale feature extraction network and a self-attention mechanism are adopted to extract image features, a cross-modal mapping model is constructed, super-resolution conversion is performed through a generative adversarial network, and image details and definition are improved. And finally, monitoring the quality of the super-resolution image, evaluating the conversion effect, and adjusting the processing strategy according to the quality coefficient to ensure that the output image meets the medical diagnosis requirement.

A non-transitory computer readable medium (107, 127) stores instructions readable and executable by at least one electronic processor (101, 113) to provide an operating mode for a medical device (120) to provide medical diagnostic and / or medical treatment functionality; instructions readable and executable by the at least one electronic processor to provide a service mode for the medical device that provides service functions for servicing the medical device; and instructions readable and executable by the at least one electronic processor to: perform a validation process at an end of a servicing session of the medical device performed using the service mode to determine whether the medical device is in an incorrect operating state; and display, on a display device (105) operable by a service engineer and in response to determining the medical device is in the incorrect operating state, an indication that the medical device is in the incorrect operating state.

The invention relates to a medical image generation method and device based on a migration model, computer equipment and a storage medium, and aims to ensure data quality and consistency and lay a foundation for model training by acquiring and preprocessing a medical image report data set and generating an initial medical image and corresponding initial pathological text data. And constructing a text-to-image generation model based on a diffusion model, and preliminarily realizing text-to-image conversion. The generation model is finely adjusted by using initial data, and the generation precision and adaptability are improved. And analyzing the multiple pieces of target pathological text data, generating a target medical image by using the optimization model, and verifying the validity of the model in practical application. According to the technical scheme, transfer learning and a diffusion model are combined, the problems of medical data finiteness and distribution inconsistency are solved, the medical image generation effect and application value are improved, and important technical support is provided for clinical research and medical diagnosis.

Processing of medical diagnostic information returns comprises receiving a text block containing medical diagnostic information and returning corresponding tracking codes. Diagnostic terms may be identified within a text block containing medical diagnostic information, and the diagnostic terms may be mapped to corresponding respective tracking codes. At least one trained machine learning model, such as a large language model and / or a classifier, may be used to identify the tracking codes that correspond to the diagnostic terms.

The invention discloses an attention deficit hyperactivity disorder subtype recognition method based on brain network topology hub deviation, relates to the technical field of medical diagnosis, and has the technical key points that a norm model of a brain structure form similarity network is constructed based on multi-center big data; quantifying a brain network topology hub index as a target phenotype of the norm model; then, performing semi-supervised clustering analysis by utilizing the individual deviation phenotype of the topological hub index so as to divide different biological subtypes and reveal unique clinical and biological characteristics of the biological subtypes; finally, strict cross validation is carried out in an external independent queue, and it is ensured that the potential biological subtypes recognized by the typing model have good generalization and clinical effectiveness.

The invention relates to the technical field of medical diagnosis, and particularly discloses a pregnant woman self-management ability evaluation and analysis management method, which comprises the following steps: providing a module of related knowledge points of gestational diabetes in pregnant woman terminal equipment or application, and enabling a pregnant woman to learn and test through the module to obtain the mastering condition of the pregnant woman on knowledge; real-time monitoring is carried out through a pregnant woman terminal device or application, and health data and daily management feedback of a pregnant woman are collected regularly; comprehensively calculating the self-management ability level of the pregnant woman according to the health data and the knowledge mastering condition by utilizing a machine learning algorithm, and outputting an evaluation result; the health data and daily management feedback of the pregnant woman are collected in real time, the health change of the pregnant woman can be continuously monitored, the self-management effect of the pregnant woman can be reflected in time, the knowledge mastering condition and the health data of the pregnant woman are comprehensively analyzed through a machine learning algorithm, the self-management ability of the pregnant woman is accurately evaluated, and the self-management efficiency of the pregnant woman is improved. Weak links in the management process are identified, and personalized optimization suggestions are provided.

The present invention concerns a computer-implemented method (300) for enriching ambiguous, incomplete or sparse health data, comprising: obtaining an input dataset (302) comprising a plurality of electronic health records (EHRs) associated with a patient; extracting (308) health information which is explicitly recited in the EHRs from the input dataset (302), including at least one diagnosis indicated by a name of a disease (504) or a medical classification code (502) which denotes a disease (504); generating (310) supplementary health information which is not explicitly documented in the EHRs based, at least in part, on the extracted health information, the supplementary health information including at least one or more symptoms (506) inferred from diseases (504) directly or indirectly documented in the input dataset (302); and validity-scoring (312) at least part of the extracted health information and the supplementary health information to produce an output dataset (314).

The invention relates to the technical field of scalp detection, in particular to a scalp detection method and system based on deep learning, and the method comprises the following steps: extracting the light intensity value distribution and spatial position value of image pixel points based on scalp image data, analyzing the regional feature boundaries of an epidermal layer, a corium layer and a hair follicle layer, and carrying out the partitioning processing of the whole region, and generating a scalp layering segmentation result. According to the method, through combined analysis of a light intensity value and a spatial position in scalp image data, layered region division is refined, and through quantification of sebaceous gland distribution area, a relation between hair follicle spacing and density and corium layer thickness characteristics, interaction characteristics of sebaceous gland secretion value, hair follicle spacing and thickness value are dynamically analyzed; the fluctuation trend of the health state in the time sequence is disclosed, the accuracy of health state analysis is improved, the efficiency and comprehensiveness of anomaly positioning are enhanced, and more scientific support is provided for medical diagnosis and beauty care.

The invention relates to the technical field of colloidal gold detection, and discloses a colloidal gold multi-index synchronous detection system for AI multi-task scheduling. The system comprises a spectral feature decoupling module which separates overlapped spectral responses based on a graph convolution network and generates a spectral fingerprint spectrum; the multi-index quantization module analyzes the nonlinear mapping relation through a variational auto-encoder to generate a quantization decision vector; the fluid dynamic modeling module is combined with a Navier-Stokes equation to invert a sample diffusion path; the signal drift suppression module suppresses background interference by applying a generative adversarial network; the task scheduling engine module adopts a Monte Carlo tree search strategy to allocate computing resources; the cross interference compensation module generates a compensation coefficient matrix by using a tensor decomposition algorithm; and the feedback module controls the micro-valve array to optimize the detection synchronism. All the modules cooperate to achieve multi-index synchronous detection, the detection precision, efficiency and anti-interference capability are improved, and the system is suitable for the fields of medical diagnosis, food safety detection and the like.

This invention relates to methods and systems relating to medical diagnostics. In particular, the invention relates to a method of processing data from a medical diagnostic system which comprises a detector arrangement configured to detect interaction of high energy particles with tissue. The method comprises receiving diagnostic data associated with interaction of high energy particles with tissue, wherein the diagnostic data is generated as a result of interaction of the high energy particles and the tissue being detected by the detector arrangement of the medical diagnostic system. The method further comprises processing the received diagnostic data with a trained machine-based classifier in order to facilitate and / or assist a medical diagnosis, wherein the trained machine-based classifier is trained at least with digital diagnostic data generated by a digital twin of the medical diagnostic system, wherein the digital twin is a computer-implemented simulation of at least part of the medical diagnostic system.

The invention provides a multi-view eye fundus image splicing method suitable for multiple modalities, and the method comprises the steps: obtaining a plurality of to-be-spliced images of different modalities, carrying out the corresponding preprocessing according to the imaging characteristics of the modalities to which the images belong, and obtaining a preprocessed image group; selecting one of the preprocessed image groups as a reference image, and performing image registration on the other images and the reference image to obtain corresponding registration image groups; on the basis of a preset registration precision threshold value and the proportion of overlapping areas between the images, screening out the images meeting the requirements from the registration image group; and performing multi-scale fusion processing according to the spatial relationship between the screened images to obtain a spliced eye fundus image. According to the multi-view eye fundus image splicing method provided by the invention, through preprocessing, registration, screening and multi-scale fusion, images of different modes can be efficiently integrated, the splicing precision and the image quality are improved, and the method is suitable for accurate eye fundus analysis and medical diagnosis.

The invention relates to a molecular model established based on proteomics detection serum specimens and used for assisting in evaluating the renal injury progress of diabetic nephropathy as well as a construction method and application of the molecular model, new disease diagnosis markers can be found, and an existing disease diagnosis system can be optimized; according to the technical scheme, a proteomics technology is combined with various medical diagnosis technologies such as experiments and images through research thinking logic of evidence-based medicine and clinical epidemiology so as to diagnose whether a patient suffers from diseases or not and identify different diseases, and the molecular model is formed by combining proteins P23396 + P0CG47 + Q9NYQ8 + P63241, according to the present invention, the protein composition in the sample is detected by using the high-throughput mass spectrometry means, the difference of the diabetic nephropathy disease group and the non-disease group on the proteomics level is compared, the biomarker for the disease progress auxiliary evaluation model construction is screened, and the new scheme is provided for the disease progress auxiliary evaluation of the diabetic nephropathy.

A computer-implemented, machine learning method for cross-cohort predictions from medical data. Patients of one or more source cohorts are mapped to a feature space of a target cohort based on constraints. Patient distributions of the one or more source cohorts and the target cohort are learned. The patient distributions of the one or more source cohorts are corrected for the target cohort. The method has applications including, but not limited to medical AI, drug development, medical diagnostics / applications and in healthcare, for example, to optimize predictions or support decision making.

The invention discloses an image processing method and device, equipment, a medium and a program product. The method comprises the following steps: acquiring three-dimensional image data and a two-dimensional projection image of a target bone segment; determining a target bone part in the two-dimensional projection image of the target bone segment according to the projection direction of the two-dimensional projection image of the target bone segment; segmenting the three-dimensional image data of the target bone segment to obtain three-dimensional image data of the target bone part; determining two-dimensional contour data of the target skeleton part based on the three-dimensional image data of the target skeleton part; and superposing the two-dimensional contour data of the target bone part into the two-dimensional projection image of the target bone section to generate a target image marked with the contour of the target bone part. According to the method, the display effect of the image is remarkably improved, and the readability and the information amount of the image in medical diagnosis and research are enhanced.

An evaluation apparatus according to an embodiment includes processing circuitry. On the basis of performance information related to performance of a medical diagnostic imaging device and numerical information related to at least one evaluation item, the processing circuitry makes an evaluation of a first imaging plan used by the medical diagnostic imaging device, the numerical information conforming to a guideline related to imaging plans. On the basis of a result of the evaluation, the processing circuitry generates, from the first imaging plan, a second imaging plan conforming to the guideline. The processing circuitry outputs the second imaging plan.

The invention discloses an MGBCU-based pelvic floor muscle edema focus area segmentation method, belongs to the technical field of image processing and application, and aims to solve the problem of inaccuracy in pelvic floor muscle edema focus area positioning and segmentation of an existing method. The method comprises the following steps: firstly, preprocessing an original diseased pelvic floor muscle image through a data acquisition module to ensure that the size of the image is consistent, and converting the image into a 224 * 224 standard input format; then, the processed image is segmented through a semantic segmentation network fusing a VSSM feature extraction network, a GCUP dynamic graph convolution feature aggregation network and an SU feature fusion up-sampling module, the VSSM feature extraction network extracts local and global features of the image through a multi-layer coding stage, and the GCUP method combines the features through a dynamic neighborhood graph to obtain a multi-layer coding image; and the SU module carries out feature fusion on multiple scales so as to obtain more accurate focus region segmentation. And finally, training the segmentation model through a training module, calculating loss by adopting a cross entropy loss function, and generating a model capable of efficiently segmenting the pelvic floor muscle edema focus area through optimization of 500 learning cycles. By means of the method, accurate and efficient segmentation of the pelvic floor muscle edema focus area can be achieved, and therefore reliable support is provided for related medical diagnosis and treatment.

The present technology relates to devices and systems for multidimensional data visualization and interaction in an augmented reality, virtual reality, or mixed reality image guided surgery. The disclosed embodiment provides a tool for a physician or other medical specialist to load and review medical scans in an AR / VR / MR environment, assisting medical diagnostics, surgical planning, medical education, or patient engagement.

The invention relates to a fluorescence in-situ hybridization image result analysis method and system based on deep learning, and a medium. The method comprises the following steps: constructing an SEAM-Unet + + image segmentation model; a YOLO-SEM small target detection algorithm model is constructed; obtaining a cell precise segmentation map of a channel B; obtaining a red fluorescence probe distribution map; obtaining a green fluorescent probe distribution map; and combining the obtained accurate cell segmentation map, the red fluorescence distribution map and the green fluorescence distribution map into one map to obtain a relational graph of cell and probe distribution. According to the method, complex image scenes can be effectively processed, the analysis of various medical images is supported, the medical diagnosis efficiency is improved, personal errors are reduced, and the cell analysis and pathological detection capabilities in scientific research and clinical application are enhanced.

The invention relates to the technical field of biological and medical diagnosis, in particular to a biomarker for predicting whether a patient suffering from pyotoxic myocardial injury has a short-term death risk or not and application of the biomarker, and the biomarker is the ratio of erythrocyte distribution width to albumin. According to the method, retrospective queue research design is adopted, two data sets, namely MIMIC-IV and eICU-CRD, are used, suppurative myocardial injury patients meeting conditions are included, covariants such as baseline features, laboratory inspection results and complication information of the patients are collected, the patients are divided into two groups according to RAR medians, the relation between RAR and short-term death of the patients is analyzed by adopting multiple statistical methods, and the accuracy of the short-term death of the patients is improved. A risk prediction model of short-term death of the patient suffering from the pyotoxic myocardial injury is constructed, so that a clinician can identify the patient suffering from the pyotoxic myocardial injury with high death risk in an early stage, a personalized treatment strategy can be formulated more accurately, the survival rate of the patient suffering from the pyotoxic myocardial injury is increased, and the method has a wide application prospect.