32results about How to "Improve clinical utility" patented technology

The invention relates to the technical field of image annotation, in particular to a medical image auxiliary annotation method and system based on image processing, and the method comprises the following steps: obtaining medical image data, and carrying out the edge enhancement processing of the image data; performing preliminary labeling on the central necrosis layer, the edge active layer and the peripheral normal tissue layer to generate preliminary labeling areas of different focus levels; extracting textural features, morphological features and density features of each level, and converting the textural features, morphological features and density features into feature vectors for storage; forming a multi-level lesion association model; adjusting the boundary positions of the layers, and ensuring that the relative position relation between the layers is reasonable; dynamically updating the level annotation according to the change characteristics; and outputting a labeling layer containing the multi-level focus characteristics of the central necrosis area and the edge active area. Compared with an existing single-level or coarse-grained marking method, the method has the advantages that the hierarchical expression effect of the focus area is improved, and the detail level of the focus in the complex form is clearly presented.

The invention provides a brand new programmed death ligand 1 (PD-L1) level and immunotherapy response prediction algorithm based on the application of a deep learning technology in medical images in combination with methods of multi-modal feature fusion, a self-attention mechanism, adversarial learning and the like. The algorithm comprises the following steps of data preprocessing, encoder feature extraction, radiomics feature extraction, multi-modal feature fusion, PD-L1 level prediction and immunotherapy response prediction. According to the invention, the pathological image (Hamp; according to the method, a CT image (e.g., E staining section), a CT image and clinical data are integrated into a deep learning model for predicting the PD-L1 level of an esophageal squamous cell carcinoma (ESCC) patient. In addition, by extracting PD-L1 features of an immunotherapy patient, a model for predicting immunotherapy response is constructed. By fusing multi-modal data, auc of the model in a PD-L1 prediction task is equal to 0.835, auc of the model in an immunotherapy reaction task is equal to 0.806, a new thought and method are provided for related research in the field of tumor treatment, and beneficial reference is provided for clinical treatment.

A bleeding point positioning and tracking method, system, device and medium for minimally invasive surgery relates to the technical field of image processing, and comprises the following steps: obtaining a surgery video frame sequence, performing preprocessing and preliminary coding, and generating an initial spatial-temporal feature map; extracting spatio-temporal features with different resolutions in the initial spatio-temporal feature map by adopting a neural network to form a multi-scale feature map; a BLAZEN model is constructed, and based on the multi-scale feature map, an enhanced feature map is generated by using a multi-scale feature fusion method, a cross attention mechanism, a feature alignment method and a feature fusion method and is used for accurately positioning potential hemorrhagic spots; an HSN model is constructed, different weights are given to multiple scale features in the enhanced feature map, fusion calculation is carried out, and a high-quality feature map is obtained; a high-quality feature map is utilized to position and track bleeding points; and a bleeding point in the operation process can be positioned and tracked.

The invention discloses a pupil reflex real-time detection and analysis system, and belongs to the technical field of pupil detection. According to the method, pupil reflex of a single eye or two eyes is continuously detected in real time, interference factors such as blinking and eyelash shielding are filtered out, pupil image deformation caused by eye movement is corrected, and optical influences of cornea and aqueous humor are corrected; meanwhile, various stimulation sources and various stimulation modes are provided, and more stimulation sources can be expanded; corresponding detection programs are set according to different diseases, and reflex conditions of pupils are detected in a targeted mode; for examination results, multiple categories of pupil reflex parameters are defined, feature parameters are selected to establish a feature database of normal people and people with different diseases, and an intelligent classification method is provided for clinical diagnosis reference; according to the invention, the measurement precision is improved, the application field is expanded, and the clinical practicability is improved.

The invention discloses a frozen embryo transplantation outcome prediction method based on multi-modal data, belongs to the field of medical artificial intelligence, and is suitable for single embryo and double embryo transplantation. The method comprises the following steps: firstly, acquiring two high-resolution embryo images and corresponding clinical data of a patient, and copying the images during single embryo transplantation; the image resolution is unified by fixing the aspect ratio of an original image and properly cutting and filling. A standard picture enhancement technology is adopted for model training, and adaptability to variable imaging conditions is improved. During prediction, two preprocessed images share weights in a network with ResNet-50 as a trunk, and feature extraction is enhanced by combining a CBAM attention mechanism and a feature pyramid network. And the extracted features are averagely pooled and then directly connected with the output of a full-connection network for processing clinical data of the patient. And finally, through a two-layer full-connection network and a Sigmoid activation function, obtaining a prediction result of embryo transplantation by using binary threshold mapping.

The invention discloses a similar surgery picture retrieval method, system and equipment for minimally invasive surgery based on deep learning and a medium, and relates to the technical field of image processing. Respectively extracting original image features in the preprocessed video stream and original text features in the preprocessed text content; performing interactive fusion on the original image features and the original text features by adopting a feature fusion module; using a feature codebook module to map the fusion feature into a codebook vector; a mapping feature decoding module is adopted to decompose the codebook vector into compressed image features and compressed text features, finally, the compressed image features are decoded into similar images, and the compressed text features are decoded into text descriptions corresponding to the similar images; and the operation picture can be quickly and accurately retrieved.

The invention relates to the technical field of sewage treatment, and discloses a sewage biochemical treatment process abnormity intelligent early warning method and system based on image recognition, and the method comprises the steps: periodically collecting a sludge image and water quality sensing data; extracting floc form, bubble distribution and color texture features of the image, and performing space-time alignment fusion with the sensing data to construct a multi-source fusion feature matrix; inputting the matrix into a pre-trained digital twin evaluation model, calculating a dynamic deviation degree between a current state and a normal working condition, and identifying an abnormal mode; and generating a graded early warning signal according to the deviation degree and the abnormal mode and pushing the graded early warning signal. The system comprises an online image acquisition unit and a water quality sensor array which are used for data acquisition, and a feature processing module used for feature processing and fusion. According to the scheme, early-stage, accurate and intelligent early warning of abnormality in the sewage biochemical treatment process is realized, the false report and missing report rate is reduced, and the accuracy and the reliability of the system are improved. And the operation stability and the regulation and control efficiency of the system are improved.

The invention discloses a severe patient blood pressure trend monitoring and intervention decision-making system based on deep learning, and relates to the technical field of medical information processing, which comprises the following steps: acquiring a continuous invasive arterial pressure waveform and carrying out pulse-by-pulse segmentation, and extracting pulse-by-pulse average pressure and a multi-dimensional high-frequency waveform characterization quantity; and calculating a voltage-sharing deviation amount, a high-frequency retention amount and a steady-state collapse eigen index in combination with preorder analysis window data, inputting the data into a time sequence deep learning network to obtain a pseudo trend probability, further obtaining a corrected voltage-sharing slope and a real trend slope, respectively calculating a link checking priority and a real low-voltage intervention priority, and outputting an auxiliary intervention decision. According to the invention, link distortion and real blood pressure deterioration can be distinguished, and the accuracy of trend monitoring and intervention decision is improved.

The invention discloses a multi-source collaborative dynamic time sequence TCP prediction method and system, a medium and a program product, and the method comprises the steps: collecting multi-source heterogeneous data, including DVH data, CT data, CPP data and longitudinal follow-up data of a plurality of time nodes, of a patient in a whole radiotherapy period; performing hierarchical preprocessing and data format unification on the multi-source heterogeneous data; constructing a dynamic time sequence feature fusion matrix containing a time dependency relationship; constructing a deep learning model integrating a time sequence processing unit and a cross-modal fusion unit, wherein the model supports an incremental learning iteration updating mechanism; using the model to output TCP prediction results of a new patient at different time nodes; and if the new patient is a special case, calling the clinical rule adaptation model, and correcting the TCP prediction result by adopting a mixed correction strategy combining rule matching and doctor experience weight. According to the method, multi-source heterogeneous data can be deeply fused, time dynamic association is captured, modal feature contribution degree is quantified, continuous iterative updating is supported, and individual differences are adapted.

The invention provides an after-myocardial infarction brain injury risk prediction method and system based on multi-modal data fusion, and relates to the technical field of medical information processing, and the method comprises the steps: firstly obtaining a heart image, a brain image and a brain tissue microwave echo signal of a patient; generating waveform data based on the phase difference and the amplitude difference of the echo signals; taking the heart feature data, the brain feature data and the waveform data as nodes respectively, and establishing connection edges among the nodes according to a preset clinical knowledge base to form a heterogeneous graph; processing the graph by using a graph neural network to obtain associated features; and finally, inputting the associated features into a multi-task learning model, and outputting a future brain injury risk probability and a self-regulation function damage degree result. The accuracy and comprehensiveness of myocardial infarction after-brain injury risk prediction are improved.

The first aspect of the invention is to disclose a method for constructing a white matter high-signal focus progress prediction model. The second aspect of the invention is to disclose an application method of the white matter high-signal focus progress prediction model constructed by the method. According to the method, clinical characteristics (such as age, BMI and blood sugar) and image indexes (such as FA, MO, ICVF and ISOVF) are fused, so that the limitation of single-modal data prediction is solved, and the accuracy and comprehensiveness of WMH progress prediction are remarkably improved; the prediction algorithm is packaged into executable software (. Exe), the Windows platform off-line operation is supported, the defect that the prior art is lack of mature software tools is overcome, and clinical popularization and application are facilitated; the model can quantify the contribution degree of each feature to a prediction result, provides an intuitive decision basis for doctors, and improves the practical value of the model in clinical practice.

This application provides a multimodal ultrasound intelligent identification method and precision diagnosis system for thyroid lesions. The method determines image data blocks with multimodal spatial registration and grayscale-contrast temporal alignment. Based on the grayscale ultrasound image sequence in the image data blocks, a first depth feature map of the target user's thyroid region is determined. A second depth feature map of the target user's thyroid region is determined based on the elastography map in the image data blocks. The hemodynamic spatial distribution characteristics of the parametric map in the image data blocks are captured to determine a third depth feature map of the target user's thyroid region. Cross-modal fusion is performed on the first, second, and third depth feature maps, and then the lesion segmentation mask, benign / malignant probability value, and risk classification of the target user's thyroid region are inferred and output in parallel. Using the scheme of this application, high-precision spatiotemporal alignment and cross-modal depth feature fusion of multimodal ultrasound images can be achieved to complete end-to-end intelligent identification of thyroid lesions.

The application discloses a rapid detection method of integration hot spots based on exogenous genetic material insertion sites, uniquely encodes chromosome-site information of all ISs to obtain a digital Y representing the chromosome and the integration position; sorts Ys corresponding to all ISs; for each IS in the insertion site data set, firstly, records the IS as a CIS node C; records other nodes Vi in the insertion site data set; if the distance between C and Vi is less than a threshold TH, records Vi added to the current CIS to become a node of the CIS; simultaneously, connects the edge of C and Vi; then, continues to return to step 2, continues the next IS, and sequentially obtains the CIS network; based on the connection between all ISs, the CIS network is searched to search for a CIS meeting the condition; the application optimizes the connection searching mode and the CIS searching range, and in the detection of several integration sites, the average analysis time of the software is greatly reduced, and the clinical practicability of the CIS detection algorithm is increased.

The invention relates to the technical field of medical treatment, in particular to a medical record extraction method based on a large language model. The method comprises the following steps: performing fine-grained classification and context verification on candidate terms through a BERT-Md model, and outputting a fact support; guiding the first call of the large language model through the first composite prompt, and synthesizing a context example specific to a case; and guiding the second calling of the large language model through the second composite prompt to generate a target clinical abstract. The invention provides a large language model-based medical record extraction method, which comprises the following steps of: extracting and classifying key clinical elements from an original medical record through a BERT-Md model, and inputting the extracted key words into a large language model to generate a context example conforming to clinical logic; and ensuring that the generated abstract contains eight necessary modules through a constraint decoding technology, automatically marking an abnormal test value reference range, and outputting a clinical abstract with a standard format and standard information density.

The present invention relates to the field of gene detection. Specifically, the present invention provides a combination of 7 gene polymorphisms for guiding the use of drugs for hypertension, a kit and its application. The present invention has been verified by a large-scale prospective multicenter clinical evidence-based study, and a new combination of 7 gene sites related to antihypertensive drugs for kit detection has been determined. And based on the fluorescent Taqman-MGB probe technology, a one-step detection scheme is adopted to detect the site combination. It has been verified by a large-scale prospective clinical multicenter evidence-based study on the Chinese population that it has extremely high clinical value and effectiveness, and the operation steps are simple, the detection cost is low, the detection speed is fast, and it is suitable for clinical promotion and application.

The present application relates to the technical field of medical auxiliary apparatus, in particular to a kind of endoscopic thyroid surgery auxiliary support device, including fixed base, fixed base is equipped with support arm, support arm is equipped with support head, support arm is equipped with fixed component, adjusting assembly and monitoring component, fixed component is installed at the end of support arm away from fixed base, support arm is hollow structure, adjusting assembly is installed in support arm, monitoring component is used to real-time acquisition support head deviation data, fixed component locking torque data and the fit pressure data of support head and operation area, monitoring component is electrically connected with control module, control module is used to control the adjusting action of adjusting assembly and the locking / unlocking state of fixed component according to the data of real-time acquisition of monitoring component.The present application is used to assist fixed operation instrument in endoscopic thyroid surgery process.

The utility model discloses a multifunctional bronchoscope transfer treatment vehicle, which comprises a vehicle frame, a cover plate, a folding transfusion assembly and a disinfection transfer box, the vehicle frame is a hand-push type vehicle frame, four corners of the bottom side edge of the vehicle frame are provided with walking rollers, the front side of the vehicle frame is provided with a plurality of storage drawers, and the top side of the vehicle frame is provided with a storage bin; the bottom side of the storage bin extends into the frame, a sliding groove is formed in the top side of the storage bin, and a cover plate capable of being opened in a sliding mode is connected to the sliding groove in a sliding mode. A partition plate is arranged on the bottom side of the storage bin, and a folding infusion assembly is arranged on the partition plate. The folding infusion assembly comprises a folding frame, a top plate and infusion supports, the folding frame is an electric / pneumatic scissor type folding frame, the top plate is installed on the top side of the folding frame, at least one set of infusion supports are arranged on the two sides of the top plate, and the infusion supports can stretch into the storage bin when the folding frame is in a contraction state. A traditional emergency treatment vehicle and a disinfection transfer box are combined, and the multifunctional emergency treatment vehicle is applied to bronchoscope transfer and emergency treatment clinically and is diversified in function.

The application discloses a kind of three-dimensional full-automatic human body composition analysis method, system and medium based on CT image, method includes: acquisition CT image data and mark;Spine segmentation model is constructed and is trained, the spine segmentation model is in the jump connection part of pre-set U-Net network joins attention module and learns the overall information of spine, to make that spine segmentation model obtains better segmentation effect;Construct body composition segmentation model, and the same loss function and depth supervision method as spine segmentation model is used to train the body composition segmentation model;Based on the spine positioning result and body composition segmentation result obtained in well-trained spine segmentation model and body composition segmentation model, calculate human body composition related index and mutual relationship based on spine positioning result and body composition segmentation result.The application realizes full-automatic process by intelligent positioning to spine, simultaneously provides selectable interface, and it is convenient for user to carry out the analysis of specific organ or tissue.

The invention provides an optical system for complex system imaging, which comprises an eyepiece, an aperture diaphragm, an aberration eliminating lens group, a front field lens group, a rear field lens group and a prism group, a semi-transparent and semi-reflective mirror is arranged in the rear field lens group, light of a light source is irradiated to pupils through the eyepiece, reflected light of the eye ground comes out from the pupils, and the prism group is arranged on the eyepiece. Light passes through the eyepiece, the aperture diaphragm, the aberration eliminating lens group, the front field lens group and the rear field lens group and reaches the semi-transparent and semi-reflecting mirror, 50% of the light passes through the semi-transparent and semi-reflecting mirror and enters the prism group for RGB imaging, the other 50% of the light is reflected by the semi-transparent and semi-reflecting mirror for white light imaging, the front field lens group comprises a transmission-type deformable mirror, and the rear field lens group comprises a transmission-type deformable mirror. The fundus, the focusing surface of the aberration eliminating lens group, the focusing surface of the front field lens group and the focusing surface of the prism group are mutually conjugated, and the pupil, the aperture diaphragm and the transmission type deformable lens are mutually conjugated. According to the invention, high precision, high stability and high light energy utilization rate of the system in a complex imaging scene are ensured, and a solution is provided for multi-band and high-resolution diagnosis of fundus diseases.

This invention belongs to the field of medical device technology, specifically relating to a method and system for regulating the rotation speed of a ventricular assist device (LVAD) based on deep learning. The deep learning-based LVAD rotation speed regulation method includes: acquiring current left ventricular pressure and pump speed information; feeding the current pressure and pump speed information into a pre-trained long short-term memory (LSM) network model; obtaining the pump speed information to be regulated through the LSM network model; and sending the pump speed information to be regulated to the LVAD. This invention enables the human LVAD monitoring module to automatically adjust the pump speed according to hemodynamic changes, allowing for adaptive control of the LVAD for individual patients.

This invention provides a method for electrocardiogram (ECG) imaging inversion using real-time constraints derived from intraoperative mapping data. The method acquires multi-lead surface potential signals and initial intraoperative mapping data; registers the coordinate system of the initial intraoperative mapping data to the coordinate system of an individualized heart-trunk geometric model, obtaining a spatial mapping relationship; generates a mapping weight matrix based on the data quality of the initial intraoperative mapping data; constructs a joint inversion objective function based on the multi-lead surface potential signals, the forward transfer matrix, the initial intraoperative mapping data, the spatial mapping relationship, and the mapping weight matrix; acquires newly added intraoperative mapping data and inputs it into the joint inversion objective function for incremental solving, obtaining the final cardiac electrical activity reconstruction result; and performs visualization imaging processing on the final cardiac electrical activity reconstruction result to obtain the final inversion imaging result. This reduces the inversion uncertainty caused by model errors, improving the accuracy and clinical applicability of ECG imaging.

The present application relates to a kind of feeding intolerance risk assessment method and system based on multi-source medical data, comprising: the change trend feature of postoperative key biochemical index is extracted to laboratory test data Generation physiological state feature vector;Symptom entity is extracted from electronic medical record text data, and the word vector corresponding to each symptom entity is aggregated, and generate symptom text feature vector;Physiological state feature vector and symptom text feature vector are fused to construct comprehensive feature vector;Utilize the activation vector of path to enhance comprehensive feature vector and obtain enhanced feature vector;Enhanced feature vector is input into the risk assessment model of pre-setting, and the preliminary risk probability is obtained;From electronic medical record text data, identify the risk reverse index of pre-setting, if identification, then according to the activation intensity of recovery path in path activation vector Determine adjustment factor, adopt adjustment factor to down-regulate the preliminary risk probability, obtain feeding intolerance risk assessment value.

The invention relates to an intelligent pressure bra and a control method thereof. Comprising a bra main body, a pressure sensing module, a posture sensing module, a pressure adjusting module and a central control module, the pressure sensing module, the posture sensing module and the pressure adjusting module are fixedly connected to the bra main body; the pressure sensing module is used for collecting original chest pressure signals of a patient; the posture sensing module is used for collecting an original posture signal of a patient; the pressure adjusting module and the pressure sensing module are correspondingly arranged; the central control module is connected with the pressure sensing module, the posture sensing module and the pressure adjusting module and used for processing data, communicating with remote terminal equipment and controlling the pressure adjusting module. Compared with the prior art, the method has the advantages that real-time closed-loop adjustment is realized; the compression strategy is dynamically optimized in combination with the posture of the patient, and the safety and accuracy of postoperative rehabilitation are improved.

This invention relates to a myocardial repair patch based on multi-material printing, its preparation, and its application, belonging to the field of bio-3D printing and regenerative medicine technology. The invention uses PLCL and GelMA hydrogel loaded with active cardiomyocytes as bio-inks, and introduces gelatin gel as a heat buffer material. An orthogonal network structure is constructed using multi-material bio-3D printing technology to prepare a myocardial repair patch with excellent dynamic adaptability to the myocardial interface and good biocompatibility. The myocardial injury repair patch prepared by this invention achieves a structure-function integrated design through the synergistic effect of the three materials, significantly overcoming the limitations of single materials in terms of mechanical properties, biological function, or thermal compatibility. The mechanical properties of the myocardial injury repair patch prepared by this invention can precisely match those of natural myocardium, while possessing high cell activity, effectively inhibiting fibrosis, improving myocardial function, and achieving true active repair. Furthermore, the process conditions are controllable, demonstrating good translational potential.

The invention relates to adipose tissue lipid metabolites for evaluating the health state of fat and a detection kit and application of the adipose tissue lipid metabolites. Specifically, the lipid metabolites arachidonic acid and docosapentaenoic acid can be used as markers for evaluating the health state of adipose tissue metabolism; the arachidonic acid can be used for improving obesity metabolic disorder; according to the kit, fat tissue lipid metabolites are rapidly detected, so that the fat tissue is directly and rapidly evaluated; according to the detection kit, the technical requirements on operators are reduced, the operation steps are simplified, and the detection kit can be applied on a large scale, so that early detection and prevention and treatment of obesity-related diseases are improved.

This application discloses an intelligent triggering, matching, and closed-loop quality control system and method for intraoperative awakening decision-making in brain tumor surgery, relating to the fields of medical artificial intelligence and clinical decision support technology. The system comprises five modules: data acquisition, feature extraction, disease matching, report generation, and closed-loop feedback. It achieves full-process intelligence through two-layer rule-based screening of target patients, multi-dimensional weighted similarity matching of historical cases, generation of clinical decision reports using a large language model, and closed-loop data accumulation at multiple postoperative time points. The method operates according to the system's execution, with physician quality control links at each key node. This invention solves the problems of traditional decision-making relying on experience, data fragmentation, and lack of closed-loop feedback, improving the objectivity and accuracy of intraoperative awakening decisions, constructing a human-machine collaborative quality control system, and enabling the system's autonomous learning and evolution.

A method, system, device and medium for locating and tracking bleeding points in minimally invasive surgery, relating to the field of image processing technology, including obtaining a surgical video frame sequence, performing preprocessing and preliminary encoding, and generating an initial spatiotemporal feature map; using a neural network to extract spatiotemporal features of different resolutions in the initial spatiotemporal feature map to form a multi-scale feature map; constructing a BLAZEN model, based on the multi-scale feature map, using a multi-scale feature fusion method, a cross-attention mechanism, a feature alignment method and a feature fusion method to generate an enhanced feature map for accurately locating potential bleeding points; constructing an HSN model, assigning different weights to multiple scale features in the enhanced feature map and fusing and calculating them to obtain a high-quality feature map; using the high-quality feature map to locate and track bleeding points; and being able to locate and track bleeding points during surgery.

The application discloses a marker combination based on ubiquitination related genes and application thereof in breast cancer prognosis and chemotherapy sensitivity evaluation. Four ubiquitination related genes, CBLL1, RNF13, TRIM59 and E4F1, are used to form a gene risk score: Risk score=(expression amount of E4F1*0.040)+(expression amount of CBLL1*-1.194)+(expression amount of RNF13*-0.777)+(expression amount of TRIM59*-0.826), and then a nomogram model is constructed by integrating the Risk score and TNM clinical stage, and the model shows extremely high prediction accuracy. The application also proves for the first time that E4F1 is a key gene for promoting breast cancer paclitaxel resistance and migration / invasion, and verifies that targeted inhibition of E4F1 can significantly enhance the efficacy of paclitaxel, and has definite therapeutic conversion potential.

The application relates to a lung cancer drug resistance risk assessment system based on multi-modal data and a light network, relates to the technical field of lung cancer drug resistance risk assessment, and comprises the following: a data clustering and division module, which is used for acquiring sample multi-modal data and sample drug resistance data of historical patients, extracting a response distribution mode for clustering and division, and acquiring a plurality of response subgroups; a network library construction module, which is used for training a plurality of specific evaluation networks to form a specific evaluation network library; a mode matching and searching module, which is used for acquiring a target response distribution mode of a target patient and performing network matching; and a drug resistance risk assessment module, which is used for acquiring target multi-modal data of the target patient, combining a network matching result to perform risk assessment, and generating a drug resistance risk assessment result. The application solves the problem that a traditional evaluation method mainly depends on single-modal data, the information is single, the evaluation accuracy is poor, and it is difficult to adapt to individual differences of patients.