74 results about "Clinical value" patented technology

The invention relates to the technical field of cardiovascular examination, in particular to a cardiovascular ultrasonic examination quality control method and system based on artificial intelligence, and the method comprises the following steps: obtaining a valve motion image through ultrasound, extracting a valve leaflet edge coordinate, recognizing a valve opening center and a valve leaflet tip through a convolutional neural network, and generating motion data; the method comprises the following steps: calculating a deviation degree based on trajectory fitting, judging stability, analyzing peak values of a systolic period and a diastolic period, calculating a symmetry difference, extracting a valve opening area, carrying out self-encoder analysis in combination with the symmetry difference to generate a fluctuation amplitude, and carrying out normalization processing to complete hierarchical classification so as to generate a quality control result. By acquiring leaflet edge points and combining a convolutional neural network to identify key features, accurate extraction of motion data, finer trajectory fitting and offset calculation, more scientific quantitative evaluation of symmetry difference and more stereoscopic area fluctuation and feature fusion analysis are realized, hierarchical and hierarchical synchronization is realized through normalization processing, and the accuracy of the motion data is improved. And the result is more credible, more stable and higher in clinical value.

The invention discloses a structured information extraction system for a mental disorder electronic medical record based on a knowledge graph and a natural language, and belongs to the technical field of medical information processing. According to the system, firstly, core concepts such as diseases, symptoms and drugs are extracted from an authoritative guide to construct a mental disorder knowledge graph, and a standardized clinical knowledge base is established; then pre-training and fine-tuning the deep learning model on a large number of biomedical texts and desensitized medical records to enable the deep learning model to have a medical language understanding ability; performing preprocessing, named entity recognition and entity linking on the electronic medical record text, and mapping spoken expressions to standard medical terms; inference is carried out by utilizing a relation extraction model and combining with a knowledge graph to complement implicit clinical information; and finally, structured data output meeting the standards of FHIR and the like is generated. According to the method, through deep fusion of knowledge driving and data driving, the problems of insufficient semantic understanding and weak generalization ability of a traditional method are effectively solved, and the accuracy and clinical value of electronic medical record structured information extraction are remarkably improved.

The invention relates to the field of intelligent medical treatment, in particular to a traditional Chinese and western medicine multi-modal data association network construction method and device and a program product. Comprising the steps of S1, acquiring a traditional Chinese medicine inquiry data set and a western medicine clinical data set of a patient; s2, performing first feature extraction on the traditional Chinese medicine inquiry data set to obtain N time sequence traditional Chinese medicine features X1, wherein N is the number of doctor seeing times; s3, performing second feature extraction on the western medicine clinical data set to obtain N time sequence western medicine features Y1; s4, the correlation between the Mth time sequence traditional Chinese medicine feature and the Mth time sequence western medicine feature is calculated to obtain a traditional Chinese medicine related feature X2 and a western medicine related feature Y2 which have an incidence relation, M is smaller than or equal to N, Y2 is smaller than or equal to Y1, and X2 is smaller than or equal to X1; and S5, taking the Western medicine related features as labels, obtaining the traditional Chinese medicine related features corresponding to each Western medicine related feature based on the association relationship, and generating an N * Y2 Western medicine related feature-traditional Chinese medicine related feature association network. The application has good clinical value.

The invention belongs to the technical field of medical image processing, and particularly relates to a left-hand X-ray image double-stage bone age evaluation system based on cross-modal learning. The system comprises a data preparation module, a coarse granularity classification module, a fine granularity regression module and an output module. The method comprises the following steps: firstly, preprocessing a hand X-ray image, and constructing cross-modal feature input in combination with structured text description of a standard bone age map; through an SBA-CLIP + cross-modal learning model, alignment and fusion of image features and text features are realized, and coarse-grained classification of bone age intervals is completed; and according to a classification result, dynamically calling a fine classification sub-model of a corresponding interval, and realizing fine regression prediction of the bone age. In the process, a bimodal attention alignment module is introduced to enhance internal feature representation of images and texts, and cross-modal alignment and classification are improved in combination with a comparison loss function guided by cyclic consistency. According to the method, the prediction precision and interpretability are remarkably improved, and the method has wide application prospects and clinical value.

The invention relates to the technical field of medicine, and provides a medicine clinical value evaluation method and system, electronic equipment and a storage medium, and the system comprises a medicine information collection module which is used for obtaining first information of a to-be-evaluated target medicine; the evaluation standard construction module is used for setting an evaluation standard based on a preset evaluation requirement; the standard quantitative assignment module is used for performing weight assignment on the evaluation standard; the evaluation evidence integration module is used for acquiring second information of the target drug based on the evaluation standard set by the evaluation standard construction module and the first information; and the drug value evaluation module is used for evaluating the clinical value of the target drug based on the second information of the target drug by applying an evaluation standard. The method and the device are used for overcoming the defects of dimensionality stiffness, quantization distortion, evidence dispersion and decision lag during evaluation of the clinical value of the medicine in related technologies. The method and the device can be used for realizing scientific evaluation, dynamic management and scenarized decision of the clinical value of the medicine.

The invention discloses a radiotherapy plan automatic optimization method and device based on a large language model and RAG, and the device comprises an initial plan generation module which is used for generating an initial scheme based on a fixed weight; the data construction module is used for establishing a clinical knowledge base and completing semantic segmentation and vector indexing; the retrieval module is used for matching the query vector with a knowledge base, and obtaining a weighted knowledge set through similarity screening and reordering; the enhancement prompt generation module is used for generating an enhancement prompt; the large language model evaluation module is used for evaluating a scheme and outputting a weight adjustment suggestion; the iterative optimization module is used for updating parameters and generating a new scheme until convergence; and the comprehensive evaluation module analyzes the candidate schemes and outputs an optimal radiotherapy plan. According to the method, the large language model and the RAG are combined, clinical knowledge dynamic introduction and weight adaptive optimization are realized, manual intervention is reduced, target coverage and endangered organ protection are both considered, and radiotherapy plan intelligence and clinical value are improved.

The embodiment of the invention discloses a gynecological malignant tumor postoperative home nursing and system. The method comprises the following steps: determining patient information corresponding to a patient to be nursed, wherein the patient information comprises physiological data and malignant tumor postoperative data; determining a real-time health state of the to-be-nursed patient based on the physiological data and the malignant tumor postoperative data; inputting the real-time health state into a preset nursing method atlas database, and determining a home nursing method corresponding to the patient to be nursed based on the preset nursing method atlas database; and obtaining personalized data of the to-be-nursed patient, and correcting the home nursing method based on the personalized data to obtain a target home nursing method corresponding to the to-be-nursed patient. According to the application, the scientificity, safety and patient compliance of home care can be remarkably improved, and rehabilitation support which has higher clinical value and meets individual requirements is provided for malignant tumor postoperative patients.

The invention relates to the technical field of health monitoring, in particular to a foot multi-area temperature and humidity cooperative monitoring system and method for diabetic foot ulcer risk prediction.The intelligent sensing terminal is integrated with a distributed temperature and humidity sensor array, a motion sensing unit, a microprocessor and a first wireless communication module through a flexible circuit; the mobile relay terminal is internally provided with a second wireless communication module and a terminal application program, the cloud analysis platform is deployed with a time sequence database, an artificial intelligence analysis engine and a message push service, and the medical interaction terminal provides a visual interface for medical staff and patients. According to the system and the method, real early warning is realized, the accuracy and the reliability of risk assessment are improved, a complete collaborative closed-loop system is constructed, efficient energy management and excellent user experience are realized, long-term self-optimization and self-adaptive evolution capabilities are also realized, and the clinical value of the system and the method is continuously improved.

The invention discloses a construction method of an AIS patient pre-hospital delay risk prediction model, and relates to the field of medicine. Comprising the following steps: data acquisition: acquiring data through a hospital electronic medical record system and telephone return visit, and performing anonymization processing on the data after approval by an ethical committee; model construction: performing inter-group comparison by using SPSS 29.0, then screening independent risk factors of pre-hospital delay by using binary Logistic regression, and finally constructing a column diagram prediction model by using an rms packet of R 3.6.3 software; and verifying the model, and evaluating the distinction degree through the area AUC under the working characteristic curve of the subject. The pre-hospital delay prediction model for the first-onset AIS patient, constructed by the method, has good distinction degree and accuracy, provides a basis for identifying the pre-hospital delay of the first-onset AIS patient, effectively shortens the arrival time of the patient for the first-onset AIS patient, and has important public health significance and clinical value.

The invention relates to the field of intelligent medical treatment, in particular to a colposcope image-based data processing and segmentation method, equipment and a program product. The method includes: acquiring a vagina vinegar white image; performing mirror surface area detection on the vagina vinegar white image to obtain a mirror surface area; in the mirror surface area detection, a vagina vinegar white image is converted into an HIS color space to obtain a low-saturation S, high-brightness I and gradient GR three-channel vagina vinegar white image, and a mirror surface area is marked based on the three-channel vagina vinegar white image; and performing priority calculation on each pixel point in the mirror surface area, and performing patch repair processing based on a priority sequence to obtain a processed vagina vinegar white image. The application has good clinical value.

The invention relates to the field of intelligent medical treatment, in particular to a continuous time sequence CT image construction method and device based on EIT and a program product. Comprising the steps of performing CT scanning on a to-be-detected part and a to-be-detected person, and obtaining CT images of the to-be-detected person at the end of inspiration and the end of expiration and EIT impedance images of the same continuous time period from the end of inspiration to the end of expiration; the CT image at the end of inspiration and the CT image at the end of respiration are used as a first frame and a tail frame respectively, and a motion field for converting the CT image at the end of inspiration into the CT image at the end of expiration is predicted based on the dynamic change of the EIT impedance image in a continuous time period from the end of inspiration to the end of expiration; registering the motion field, the first frame and the tail frame to obtain a registered motion field, a registered first frame and a registered tail frame; and generating a CT image in a middle time period through the registered motion field, the first frame and the tail frame, and obtaining a CT image in a continuous time period from the end of inspiration to the end of expiration. The application has good clinical value.

The application discloses a kind of based on multi-source medical text construction traditional Chinese medicine diabetic nephropathy knowledge graph method and system, including following module: data integration module: integration diagnosis and treatment guideline and electronic medical record, after redundancy, terminology standardization constructs unified medical data set;Mixed labeling and entity recognition module: fusion artificial labeling and BERT-BiLSTM-CRF model automatically identifies traditional Chinese medical syndrome, traditional Chinese medicine and other complex entities;Relationship modeling module is based on semantic embedding and multi-label classification algorithm, accurately constructs traditional Chinese and western medicine association rules;Atlas application module: entity relationship is converted into attribute graph structure, supports graph database interactive query, realizes diagnosis and treatment recommendation, contraindication early warning and curative effect analysis.Through the above scheme, the present application significantly improves the accuracy of differentiation, reduces the risk of drug contraindication, provides efficient, interpretable decision support for the prevention and treatment of diabetic nephropathy, has important clinical value and popularization potential.

The invention relates to the field of intelligent medical treatment, in particular to an allergy data processing method and device and a program product. Comprising the steps of obtaining a basic data set and a risk category label of a to-be-tested person; performing data expansion on the data set and the label of the risk category through a generative adversarial network to obtain expanded data; in the generative adversarial network training process, a generator generates preliminary synthetic data by using random noise and feature information of original allergy-related medical data, a discriminator distinguishes real allergy-related medical data from synthetic allergy-related medical data, and iterative training is performed on the generator and the discriminator; loss function calculation of the generative adversarial network generator comprises adversarial loss and feature comparison loss, calculation of the adversarial loss comprises random noise data and feature data of the allergic medical data, and calculation of the feature comparison loss comprises the allergic medical data. The application has good clinical value.

The invention relates to the field of intelligent medical treatment, in particular to a pulmonary nodule segmentation model construction method and device based on traditional Chinese medicine intervention and a program product. The method includes: acquiring pulmonary nodule image data sets of a patient before and after traditional Chinese medicine intervention; the pulmonary nodule image data sets before and after traditional Chinese medicine intervention are transmitted to a segmentation model to be trained for training until a loss function is unchanged, and a pulmonary nodule segmentation model is obtained; the segmentation model sequentially comprises a convolution layer, an encoding module, a decoding module, a second convolution layer and an output layer, the encoding module comprises N encoding layers, each encoding layer comprises a positioning feature extraction layer and a residual module which are connected in series, the decoding module comprises M decoding layers, image data obtains positioning features through the convolution layers and the N encoding modules, and the N is a positive integer; and the positioning features sequentially pass through the deconvolution layer and the decoding layer and then are output through the output layer. The application has good clinical value.

The invention relates to the field of intelligent medical treatment, in particular to a data processing method and device for renal artery FFR evaluation and a program product. Comprising the following steps: acquiring continuous time sequence frame data of renal arteriography; frame selection is carried out on the time sequence frame data of the renal arteriography to obtain a multi-time sequence, the multi-time sequence comprises a key frame and N effective frames, and N is a natural number larger than 1; the multiple time sequences are output to a segmentation model for renal artery blood vessel segmentation, and renal artery blood vessel masks of key frames and effective frames are obtained; the key frame and the mask of the key frame are sequentially registered with N effective frames and masks of the effective frames based on L scales to obtain L * N registered effective frame data; and performing 2.5 D data construction based on the registered effective frame data and key frame data to obtain 2.5 D data for FFR evaluation of the renal artery. The application has good clinical value.

Systems and methods for establishing a patient's current or future clinical or lab values are provided. A neural network is trained on a dataset of medical images, such as ultrasound images, that are tagged with information concerning the lab values of people who were imaged to produce the medical images. The trained neural network can then be provided with medical images of a patient, and the neural network can then make a determination as to the patient's current or future clinical or lab values.

The application relates to the field of intelligent medical treatment, in particular to a puncture Gleason score 3+3 and 3+4 prostate cancer radical resection postoperative score upgrading prediction method, equipment and program product. The method comprises the following steps: acquiring prostate mpMRI image data of a to-be-measured person; obtaining the position of a prostate lesion based on the image data; when the position of the prostate lesion is located at the bottom, determining postoperative upgrading on the basis of the prostate cancer Gleason score grade to obtain a prediction result. The application can perform prostate cancer radical resection postoperative Gleason score upgrading prediction based on preoperative biopsy data, and has good clinical value.

The invention discloses a method and a system for predicting the mechanical property of a blood vessel and calcified plaque material. The method comprises the following steps: constructing a three-dimensional geometric model containing an aorta root blood vessel wall, an autologous valve and a calcified plaque; constructing a bracket geometric model actually implanted in the operation; using finite element analysis to simulate the implantation process of the stent, and obtaining the geometric morphology index of the simulated stent valve ring; based on the obtained geometrical morphology indexes of the stent valve ring, the material mechanical property with clinical value of the target patient is determined; obtaining material mechanical properties with clinical values of a plurality of target patients and corresponding clinical feature data thereof, and constructing a data set; based on the constructed data set, a nonlinear regression model is adopted to construct a prediction model of clinical features and material mechanical properties; and performing prediction by using the prediction model. By adopting the method and the system, the mechanical property of the individual material can be obtained noninvasively, and the mechanical property of the new patient material can be predicted by associating the mechanical property with the clinical characteristics.

The invention discloses an application of circWHSC1 as a biomarker in preparation of a product for diagnosing or treating ineffective recanalization after ischemic stroke. According to the present invention, the circRNA sequencing results show that the expression of the circWHSC1 (including hsacirc0001388 and nucirc0001336) in the ineffective recanalization patient body is significantly reduced, and the circWHSC1 is verified in the mouse brain tissue, the plasma and the thrombus model of the tMCAO model; functional studies show that the circWHSC1 can significantly reduce the cerebral infarction volume of the mouse. The circWHSC1 can be used for early diagnosis, risk assessment, severity judgment, curative effect monitoring and prognosis judgment of invalid recanalization, and can be used as a drug target for screening candidate drugs for preventing or treating invalid recanalization. The invention provides a molecular diagnosis marker and a therapeutic target for invalid recanalization, and has important clinical value.

The invention relates to the technical field of radio frequency, and particularly discloses a method for improving coarse facial pores. The method for improving coarse facial pores comprises the step of applying radio frequency to a facial area to be improved at preset power for preset time. According to the method, radio frequency is applied to the face area to be improved, the problem of coarse face pores can be remarkably improved only through one-time treatment, the process is safe and comfortable, and the method has important clinical value as an anti-aging means.

This invention discloses an automated multi-parameter assessment method, device, and medium for aortic imaging based on three-dimensional images. The method includes acquiring three-dimensional chest CT images and preprocessing them; extracting and optimizing an initial centerline based on the obtained three-dimensional vascular mask; dividing the initial centerline into ascending aorta, aortic arch, and descending aorta segments using the optimized initial centerline and the opening positions of branches on the aortic arch; extracting the average CT value of the adipose tissue surrounding the descending aorta based on the divided descending aorta segments; constructing orthogonal cross sections, performing dimensionality reduction and projection processing on each cross-sectional mask, and calculating the major and minor axes based on the farthest point pairs, outputting the major axis diameter sequence of each cross section; calculating the aortic calcification load, assessing aortic dilation and morphological variations, and evaluating the inflammatory status of the perivascular adipose tissue; and generating a comprehensive report of indicators. This invention fully utilizes existing imaging resources, improving the utilization efficiency and clinical value of medical imaging data.

The invention discloses a competing product information analysis-based medical instrument demand management method and system, and relates to the field of medical data analysis. According to the method, multi-source heterogeneous competitive product information data of the medical equipment is obtained in real time and subjected to standardized processing; extracting a data entity and a key event from the processed data, and constructing a competitive product knowledge graph associated with deep semantics; synchronously performing function-performance benchmarking analysis, clinical value and pain point analysis and technical route and patent risk analysis to obtain multi-dimensional analysis data; carrying out anomaly detection on the real-time data by adopting an improved isolation forest algorithm; the multi-dimensional analysis data and the anomaly detection result are subjected to situational fusion and intelligent reasoning through a logic mapping model, and automatic medical instrument product requirements are achieved; according to the invention, full-link, automatic and intelligent conversion from massive competitive intelligence to accurate product requirements is realized, and the market insight, risk early warning capability and product planning efficiency of medical equipment enterprises are remarkably improved.

The present application belongs to the field of intelligent medical treatment, and particularly relates to a method, device, medium and program product for predicting RMPP based on lung microvessel changes. The method comprises the following steps: S101: acquiring CT images of a pediatric MPP patient; S102: extracting the CT images to obtain quantitative PBV parameters, wherein the quantitative PBV parameters comprise BV10%, wherein BV10% refers to the percentage of blood volume in blood vessels with a cross-sectional area greater than 10 mm2 in total lung blood volume; and S103: if BV10% is higher than a first threshold value, determining that the pediatric MPP patient has a high risk of developing into RMPP, otherwise outputting a prediction result that the pediatric MPP patient has a low risk of developing into RMPP. The present application discovers the prediction effect of microvessel changes in CT on the occurrence and development of RMPP by quantitatively measuring the microvessel changes, realizes the clinical value of early diagnosis of RMPP, and thus drives early treatment in the clinic.

According to the lung fibrous tissue removing device, starting from the source, abnormal fibrous grids in a pleural cavity are safely and effectively broken, ablated or cut off in a physical or energy mode, all separated small rooms are broken through, and a plurality of independent areas are fused into a whole. Therefore, all effusion in the thoracic cavity can be thoroughly drained only through one-time puncture or a few times of puncture. The operation time can be remarkably shortened, the pain of a patient can be relieved, lung trauma and various complications caused by multiple times of puncture can be fundamentally avoided, the treatment effect and safety of pleural effusion, especially complex atrial effusion, are greatly improved, and important clinical value and social significance are achieved.

Systems and methods for anatomical shape modeling in accordance with embodiments of the invention are illustrated. One embodiment includes a method for clinical anatomy modeling, comprising obtaining imaging data of a portion of a patient's anatomy, generating a first model of the patient's anatomy based on the imaging data, providing the first model to a trained hybrid explicit-implicit neural shape model (NSM), obtaining a latent representation of the first model from the trained hybrid explicit-implicit NSM, and reconstructing a second model of the portion of the patient's anatomy using the latent representation. In a further embodiment, the second model is at a higher resolution than the first model. In a yet further embodiment, the method further includes steps for providing the latent representation to a classification model trained to classify latent representations to clinical values.

The present application relates to the technical field of rectal cancer CTV segmentation, in particular to a rectal cancer CTV segmentation method based on CViL-UNet, comprising the following steps: preprocessing rectal cancer CT image data, converting a 3D CT sequence into a multi-channel 2D input format, removing image noise and intensity non-uniformity, and standardizing the pixel value range to adapt to the CViL-UNet model input. The present application realizes accurate identification of the key areas of CTV primary tumor, subclinical spread area and micro-infiltration focus through local-global feature cooperation and high-frequency detail enhancement, solves the pain points of missing micro-infiltration and misjudging healthy tissue in traditional methods, can process conventional CT images without intestinal preparation, breaks the dependence of traditional methods on ideal image conditions, and the automatic and real-time segmentation process in clinical value eliminates the subjectivity and inefficiency caused by manual intervention, while meeting the dual requirements of millimeter-level precision and rapid deployment for radiotherapy planning.

This application relates to the field of intelligent healthcare, specifically to a method and program product for breast symmetry assessment based on deep learning. It includes: S1: acquiring a torso image; S2: segmenting the torso image into breast regions to obtain segmented images; S3: calculating the areas of the left and right breast regions based on the segmented images; S4: extracting depth information from the torso image to obtain depth information images; S5: calculating the volumes of the left and right breasts based on the areas and depth information images; S6: comparing the absolute differences in the areas and volumes of the left and right breasts to obtain the assessment result of breast symmetry. This application can automatically and quickly identify breast features and assess breast symmetry, possessing significant clinical value.

The application discloses a kind of based on dual-energy X-ray spinal osteoporosis grading diagnostic device and diagnostic method, dual-energy X-ray emission module: contain vertical and horizontal two groups of X-ray source (model: M200 microfocus X-ray tube, focal size ≤0.1mm), vertical group is set in the top central of scanning bed (120cm from bed surface), horizontal group is symmetrically set in the scanning bed both sides rack (80cm from bed surface, interval 60cm);The application not only solves the core defects of prior art in diagnostic accuracy, safety, practicality, but also expands the application scenario through portability, intelligent design, provides a new technical scheme for the precise grading diagnosis and standardized treatment of spinal osteoporosis, with significant clinical value and market prospect.

The application relates to the field of intelligent medical treatment, in particular to a thyroid ultrasound image data enhancement method, device and program product. The method comprises the following steps: acquiring a thyroid ultrasound image; segmenting the thyroid ultrasound image to obtain a fascia mask and an adenoid parenchyma mask; calculating the distance from each pixel to the nearest edge pixel of the fascia mask to generate a distance map, and calculating the weight of each pixel through the distance map to generate an anatomical weight atlas; performing smoothing processing on the thyroid ultrasound image through the anatomical weight atlas to obtain an illumination layer; removing the pixel component of the illumination layer on the pixel of the thyroid ultrasound image to obtain a texture layer; performing directional filtering on the texture layer to obtain a direction selection coefficient; performing gate control on the tissue region of the adenoid parenchyma mask to obtain a tissue gate map; enhancing the texture layer through the direction selection coefficient and the tissue gate map to obtain an enhanced texture layer; and combining the illumination layer and the enhanced texture layer to obtain an enhanced image. The application has good clinical value.

Systems and methods are provided for establishing a current laboratory value or current clinical value or future laboratory value or future clinical value of a patient. A neural network is trained on a dataset of medical images, such as ultrasound images, tagged with information relating to laboratory values for a person imaged to produce the medical image. A medical image of the patient may then be provided to the trained neural network, and the neural network may then be determined with respect to a current laboratory value or current clinical value or future laboratory value or future clinical value of the patient.