997 results about "Lesion" patented technology

The invention provides a multi-modal large language model for generating a hepatocellular carcinoma key pathological diagnosis report, a framework main body is a visual coding module, and a multi-modal feature alignment module, a multi-head low-rank attention mechanism, an enhanced medical MoE mechanism and a structured output decoding layer are also introduced. The visual coding module is constructed on the basis of a Swin Transform architecture, visual pre-training is completed on hepatocellular carcinoma MRI data, and after a task specific classification head is stripped, a trunk feature extraction network is reserved to serve as an image modal representation encoder. The multi-modal feature alignment module guides the model to learn a cross-modal semantic mapping relation between a hepatocellular carcinoma MRI image and a key pathological diagnosis report language, image modal input is a visual feature sequence, and text modal output is a structured description text; and the structured output decoding layer generates six types of liver cancer focus attributes. According to the method, the pre-operative multi-parameter and multi-stage enhanced MRI image is utilized, and the open-source large model is finely adjusted to generate a matched liver cancer postoperative pathology report.

The invention relates to the technical field of medical image classification, in particular to a myopic macular traction lesion grading method and system. The method comprises the following steps: taking a convolutional neural network, a direction perception attention module and a classifier which are connected in sequence as an MTM classification model; a direction perception attention module extracts weight information of a space position through a direction perception space attention module, and a channel attention module is used for extracting weight information of a channel; an MTM classification model is used as a backbone network, direction perception attention modules and auxiliary branches which are connected in sequence are arranged after first M-1 feature coding stages of a convolutional neural network, and a self-distillation model is constructed; by combining a structural knowledge distillation strategy based on multi-stage feature fusion, a historical knowledge distillation strategy based on a linear growth mechanism and a category perception comparison learning strategy, multi-angle feature information interaction is fully utilized, multi-angle information collaborative optimization is realized, and the classification precision of the MTM classification model is effectively improved.

The invention belongs to the technical field of medical image detection, and particularly relates to an esophageal flora image intelligent detection method for risk prediction of gastroesophageal reflux disease, which comprises the following steps: acquiring flora images and clinical data, and constructing a perception network; quantifying flora displacement characteristics by using image registration; the method comprises the following steps of: extracting flora density, aggregation degree and fluorescence gradient characteristics by combining improved U-Net + + segmentation, fusing flora and epithelial cell lesion characteristics through space-time attention, generating a flora-host association map, constructing a flora dynamic evolution model by utilizing a space-time map convolutional network, predicting Barrett esophageal occurrence probability and flora diffusion trend, and predicting the occurrence probability of the Barrett esophagus. Calculating a lesion risk level through a flora imbalance quantification algorithm; in combination with reflux frequency and pH fluctuation, a flora-environment interaction model is used for simulating a field planting coefficient and correcting parameters, the parameters are transmitted to a diagnosis platform to deduce canceration risks, grading suggestions are triggered, and a visual report is generated. Therefore, the problems of long detection period, weak microscopic analysis capability and the like in the prior art are solved.

The invention provides an absorbable bioprosthetic valve design method based on artificial intelligence and biomechanics. The absorbable bioprosthetic valve design method comprises the following steps: S1, constructing a performance demand system of a valve; s2, constructing a three-dimensional reconstruction model of the original lesion structure of the human body and a parameterized structure model of the valve; s3, establishing a first deep learning model for simulating interventional mechanical behaviors of the valve; s4, constructing a second deep learning model for predicting the relationship between the stress and the material degradation behavior in the long-term use process of the valve; s5, embedding the first deep learning model and the second deep learning model into a reinforcement learning framework; and S6, carrying out simulation and experimental verification based on a design result in the step S5, and evaluating the adaptability and reliability of the design parameters under the function requirements defined in the step S1. According to the method, the biomechanical theory and the artificial intelligence algorithm are fused, the structural parameter interpretability of the absorbable bioprosthetic valve design and the automation of the whole process are realized, and a new path is provided for the intelligent optimization design of the implantable interventional medical device with a complex structure.

The purpose of the present invention is to provide: a novel therapeutic or prophylactic agent for xerophthalmia; a therapeutic or prophylactic agent for graft-versus-host disease; a corneal epithelium wound healing promoter; a corneal invasive inflammatory cell inhibitor; or an inhibitor of differentiation of lymphocytes into effector T cells. The present invention provides: a therapeutic or prophylactic agent for xerophthalmia, a therapeutic or prophylactic agent for graft-versus-host disease, a corneal epithelial wound healing promoter, a corneal invasive inflammatory cell inhibitor, a tear amount maintenance agent, a corneal epithelial damage inhibitor, and a method for preparing the same, which comprises, as an active ingredient, a substance derived from a stem cell culture supernatant; a cell proliferation marker positive cell inhibitor, or an inhibitor of differentiation of lymphocytes to effector T cells.

Example systems and techniques are disclosed that may determine at least one treatment strategy for a lesion. An example system may include memory configured to store clinical guidance and / or informatics for a PCI procedure and processing circuitry communicatively coupled to the memory. The processing circuitry may be configured to determine the plurality of treatment pathways. The processing circuitry may be configured to obtain angiogram imaging data of a coronary vasculature of a patient. The 2024 / 058837 processing circuitry may be configured to determine the clinical guidance and / or informatics based at least in part on the angiogram imaging data. The processing circuitry may be configured to output for display the angiogram imaging data and at least a portion of the clinical guidance and / or informatics, wherein the at least a portion of the clinical guidance and / or informatics is overlaid onto the angiogram imaging data.

The invention belongs to the technical field of microorganisms, and particularly relates to bifidobacterium animalis for relieving eye allergy and application of the bifidobacterium animalis. The invention provides an application of bifidobacterium animalis subsp. Lactis in preparation of a product for relieving eye allergy, the bifidobacterium animalis subsp. Lactis is Def +, and the preservation number is CGMCC (China General Microbiological Culture Collection Center) No.35798. The Bifidobacterium animalis subsp. Lactis Def < + > provided by the invention can relieve the eye itching symptom, relieve red and swollen eyelids, reduce conjunctiva and cornea injury, relieve eye discomfort, relieve globular conjunctivitis cell infiltration, improve corneal epithelium thickening lesion, improve the anti-inflammatory ability and improve allergic conjunctivitis, keratitis and blepharitis marginata in a targeted manner. The eye drops are high in safety and resistant to gastrointestinal fluid, and a safe and long-acting scheme is provided for eye allergic diseases.

The invention relates to the technical field of intelligent medical assistance, in particular to a skin disease treatment electrode positioning system based on potential distribution. The system comprises a potential gradient severe region identification module, a lesion minimum surrounding region identification module, a similar potential region grouping module, an optimal electrode position prediction module, an electric field distribution calculation module, a sweat gland dense region identification module, an optimal electrode placement point screening module, an enhanced feature generation module and a final electrode position determination module. By fusing multi-source information such as skin surface potential distribution, lesion geometric characteristics, tissue conductivity, historical treatment data and the like, systematic optimization is performed on electrode positioning in skin disease treatment, the effectiveness of electrode stimulation is maximized on the premise of ensuring the treatment safety, and the treatment efficiency is improved. An accurate electrode placement scheme is provided for treatment of different types of skin diseases, and the method is suitable for accurate determination of the electrode placement position in electrical stimulation treatment.

The invention discloses a chronic sinusitis CT (Computed Tomography) image automatic typing and severity assessment method and a chronic sinusitis CT image automatic typing and severity assessment system based on deep learning. The method comprises the following steps: acquiring paranasal sinus CT image data of a chronic sinusitis patient and an associated clinical tag; carrying out standardization processing on the CT image, wherein the standardization processing comprises gray level normalization, denoising and region-of-interest segmentation; a multi-task deep learning model is constructed, an improved 3D Re < s> Ne < t-50 > architecture is adopted by a typing sub-model to output an immune endotype classification result, and a severity evaluation sub-model segments a lesion area based on a U-Ne < t + + > structure and automatically calculates a severity level; integrating model output to generate individualized treatment suggestions; and superposing a labeling result through the thermodynamic diagram and embedding the labeling result into a hospital PACS system. Accurate typing and evaluation of chronic nasosinusitis are achieved, and diagnosis efficiency and clinical decision support capability are improved.

The invention relates to the technical field of skin lesion area reconstruction, in particular to a skin lesion area reconstruction system based on multi-modal image fusion. The system comprises a deep multi-scale feature extraction module, a skin thermal anomaly feature extraction module, a hemodynamic feature extraction module, a depth and boundary feature extraction module, a skin surface feature extraction module, a fluorescence intensity distribution and morphological feature extraction module, a first feature fusion module, a second feature fusion module and a lesion area reconstruction module. According to the method, appearance, heat, blood flow, structure and surface features are extracted from the multi-modal data, then the multi-modal image data are integrated, finally, comprehensive representation and reconstruction of skin lesion appearance, function and structure information are achieved according to the synergistic effect of the multi-modal information, and the accuracy and clinical reference value of lesion area reconstruction are effectively improved.

The invention discloses a laryngocarcinoma primary screening and lesion area positioning method and device fusing an attention mechanism. The method comprises the following steps: (1) carrying out standardization and non-uniformity correction preprocessing on a laryngoscope image; (2) constructing a parallel deep learning model; (3) designing an adaptive dynamic feature fusion (AFF) module; (4) designing a multi-objective optimization loss function suitable for a laryngeal cancer preliminary screening task; (5) constructing a dual interpretability verification system of the Grad-CAM and the SHAP; and (6) generation and visual presentation of a diagnosis result. According to the method, an Inception-v4 and ViT parallel architecture is adopted, and a hybrid dynamic attention (HDA) mechanism is introduced into an Inception-v4 branch, so that the local feature extraction capability is effectively improved. By designing an adaptive dynamic fusion (AFF) module and combining a cross-modal attention (CMAF) mechanism, efficient interaction of local and global features is realized. Particularly, a multi-objective loss function is designed aiming at the requirement of early screening of laryngeal cancer. At the output end of the model, Grad-CAM thermodynamic diagram positioning and SHAP credibility evaluation are integrated at the same time, and a complete interpretability diagnosis system is constructed.

The invention discloses an intelligent auxiliary diagnosis and grading system for gastrointestinal tumor endoscopic images, which belongs to the technical field of medical image processing and computer-aided diagnosis and comprises a multi-modal image preprocessing and segmentation module, a lesion feature extraction and diagnosis module, a grading and depth evaluation module and a closed-loop feedback optimization module. The system receives white light, a narrow band and an amplified endoscopic image, adaptive segmentation is performed to obtain a lesion area, mucous membrane morphology, capillary and gland features are extracted, Paris classification, Vienna classification and infiltration depth evaluation are realized, and segmentation parameters are subjected to closed-loop optimization according to classification confidence. And intelligent auxiliary support is provided for early diagnosis and treatment decision of gastrointestinal tumors.

The image processing device 1X includes an acquisition means 30X, a score calculation means 31X, and a classification means 32X. The acquisition means 30X is configured to acquire an endoscopic image in which an examination target is photographed by a photographing unit provided in an endoscope. The score calculation means 31X is configured to calculate scores on likelihoods of respective candidate classes corresponding to types of lesion, wherein the candidate classes are candidates for classification of an image group of the acquired endoscopic image. The classification means 32X is configured to perform the classification of the image group upon determining that at least one of the scores has reached a threshold value.

The utility model provides a ball expansion conical support which comprises a design unit and a connecting unit, the design unit comprises a plurality of support rods and a plurality of wave heads, the support rods are arranged at intervals, and every two adjacent support rods are sequentially connected in series through each wave head to form an annular structure; the number of the design units is multiple, the connecting unit is connected between the wave heads of every two adjacent design units, the radial supporting force Fn of the nth design unit from the near end to the far end of the stent is smaller than the radial supporting force Fn-1 of the (n-1) th design unit, and n is larger than or equal to 2 and smaller than or equal to 200. According to the utility model, the radial supporting force of the stent from the near end to the far end is set, so that the expanded stent can retract to different degrees at different positions under the action of the return pressure of a blood vessel in a lesion area, thereby forming a conical stent which is very matched with the conical shape of the blood vessel. The support and the conical pipeline have good fitting degree.

The invention discloses an intelligent classification and recognition method for ear-nose-throat lesion images, and relates to the technical field of image recognition, and the method comprises the steps: synchronously collecting a nasopharynx white light image and an i-Scan image, screening an image meeting a quality standard, carrying out the correlation of pathology and grading labeling, and constructing a data set containing a multi-center case; the white light image and the i-Scan image are subjected to denoising processing, key mark points are extracted, image registration is completed, a mucous membrane surface area, a submucous membrane blood vessel area and a lymphatic tissue enrichment area are divided through semantic segmentation, and feature enhancement is carried out on different areas; extracting morphological features and textural features from the enhanced image, calculating feature importance weights and fusing the feature importance weights into low-dimensional feature vectors; the benign and malignant dichotomy model and the pathological type multi-classification model are respectively constructed, and classification results are output in combination with a doctor diagnosis rule base and verification indexes, so that the accuracy and clinical practicability of ear-nose-throat lesion diagnosis are remarkably improved.

Some embodiments of a rotational atherectomy and lithotripsy system can partially or completely remove a stenotic lesion in blood vessels by rotating one or more abrasive elements to abrade and breakdown the lesion, by emitting acoustic energy to fracture and breakdown the lesion, or a combination of both.

The invention relates to application of hydroxynidone to preparation of a medicine for preventing and / or treating radiation-induced pulmonary fibrosis. Pharmacological experiments prove that the hydroxynidone has a definite resisting effect on radioactive rat lung injury including early inflammatory exudation and pulmonary interstitial fibroblast hyperplasia, and can obviously reduce pulmonary alveolar inflammatory cell exudation and reduce the content of TGF beta 1 in inflammatory exudate; the medium and large doses have the effect of delaying the development of interstitial pneumonia towards pulmonary fibrosis; the lesion degrees of the small, medium and large dosage groups are obviously reduced and are in a dose-effect relationship.

The invention relates to the technical field of intelligent lesion diagnosis, in particular to a gynecological lesion intelligent diagnosis system based on multispectral imaging, which comprises a data acquisition module, an image preprocessing module, a feature extraction module, a feature fusion module, a classification diagnosis module and an interpretability output module, obtaining a tissue multispectral image data cube by using a tunable LED array and a snapshot multispectral sensor; the preprocessing module corrects, registers and standardizes data in sequence; the feature extraction module extracts spectral features by using a one-dimensional CNN and extracts spatial features by using MobileNetV2 in parallel; the fusion module is used for weighting fusion features by an attention mechanism; the classification module outputs normal, low-degree and high-degree lesion probabilities by using a full-connection neural network; and the interpretability module generates a thermodynamic diagram to position lesions, extracts key spectral bands and displays the key spectral bands. By optimizing the image acquisition parameters, the signal-to-noise ratio and the lesion contrast ratio of the image are remarkably improved, and powerful technical support is provided for gynecological lesion diagnosis.

The invention discloses a skin lesion segmentation method and system based on dual-path perception multi-stage fusion, and relates to the technical field of medical image processing, and the method comprises the steps: carrying out the block division of a skin image, inputting into an encoder, and filtering a key lesion region through employing a region sparse attention mechanism; performing down-sampling on the feature map by using a block merging operation, and constructing a multi-scale feature pyramid; skin image features are processed by using a dual-path sensing multi-stage fusion network, deepest features generated by an encoder are processed by a spatial frequency dual-path cascade sensing module, and two-stage space-frequency collaborative optimization is executed; the method comprises the following steps: establishing jump connection between an encoder and a corresponding decoder through a space channel double-path parallel sensing module, recovering spatial resolution through block expansion operation in combination with modulated encoder characteristics, and generating a pixel-level lesion probability graph. According to the method, the context sensing capability across the space domain and the frequency domain is remarkably enhanced, and an accurate and detailed skin lesion segmentation result is obtained.

Some embodiments of a rotational atherectomy device can remove (partially or completely) stenotic lesions in blood vessels by rotating one or more abrasive elements in an orbital path to abrade and breakdown the lesion. In particular implementations, multiple abrasive elements are arranged along a distal portion of a drive shaft with an improved configuration so as to facilitate both efficient navigation into vessels extending from the abdominal aorta such as the common iliac artery, the external iliac artery, the internal iliac artery, the profunda artery, the gluteal artery, and the pudental artery and effective orbital paths for abrading stenotic material in such vessels and junctions between such vessels.

A method may include obtaining input data relating to a target treatment plan for performing radiotherapy on a lesion using a radiation device. The input data may include a first target image of the lesion. The method may also include obtaining a segment shape estimation model. The method may also include estimating, based on the segment shape estimation model and the input data, a plurality of target location combinations of the target treatment plan and a plurality of target segment shapes of a collimator of the radiation device. One of the plurality of target location combinations may indicate a location of the collimator relative to the lesion. Each of the plurality of target segment shapes may correspond to one of the plurality of target location combinations.

The invention relates to the technical field of image recognition, in particular to a multi-scale osteosarcoma CT image lesion area detection method based on feature distillation. The method comprises the following steps: acquiring a multi-scale osteosarcoma CT image and an attachment area image, performing forged image difference reduction to generate a unified CT image, reconstructing a three-dimensional tumor body form, extracting a bone attachment structure, performing relocation registration to obtain tumor body relocation data, and then generating a simulation attachment area framework based on the data, the method comprises the following steps: performing static feature distillation on a three-dimensional tumor body form to obtain an edge contour, defining an initial attachment area frame, performing feature comparison through a historical contour image to extract form change, evaluating the erosion degree of the attachment frame, and finally screening candidate lesion areas and positioning osteosarcoma lesion areas according to change areas. According to the invention, more efficient multi-source heterogeneous image data integration, more accurate three-dimensional tumor simulation reconstruction and clearer lesion area detection are realized.

Provided herein are devices and methods for the treatment of skin conditions. A skin treatment apparatus according to the present disclosure generally includes a treatment head defining a treatment space, the treatment head having a body forming said treatment space. The body is further configured to contact the treatment space to a treatment surface containing a lesion. A treatment media is disposed within the treatment space. The skin treatment apparatus also includes a heating element configured to heat the treatment media.

A method for visualizing a patient shoulder anatomy is provided. The method includes receiving image data of the patient shoulder anatomy, identifying a boundary of a lesion on a humerus based on the image data, generating one or more 3D models based on a segmentation of the image data, determining a location of a glenoid track corresponding to a contact between the humerus and a glenoid based on the one or more 3D models, generating a first virtual object based on the location of the glenoid track, and displaying: at least a portion of a rendering of the one or more 3D models, the boundary of the lesion, and the first virtual object.

The invention provides an image-based eye lesion grading analysis method and device, a medium, a program product and a terminal, and the method comprises the steps: obtaining one or more eye lesion images, inputting the one or more eye lesion images to a pre-trained first model, and generating a corresponding eye feature vector; for a single image, calculating the similarity between the feature vector and each eye disease category, and outputting a prediction category with the highest similarity; and for a plurality of images, respectively calculating the similarity between the feature vectors and each category, and realizing adaptive weighted integration by using the second model to obtain a final prediction category. Sub-model subdivision and risk level layering are carried out according to prediction categories, and a structured risk layering report is output. The problem that in the prior art, the diagnostic value of multi-image information in complex cases is difficult to effectively evaluate is solved, the accuracy of ultrasound in serious vitreous lesion and intraocular tumor recognition is remarkably improved through a self-adaptive weighted integration mechanism, high-risk patient screening and clinical decision making are supported, and the application scene of ultrasound in ophthalmic diagnosis is expanded.

The invention relates to the technical field of tobacco prevention and control, in particular to a green tobacco prevention and control method and system based on growth simulation, and the method comprises the steps: obtaining image data and environment parameters of tobacco plants, and carrying out the growth stage recognition processing of the image data, and obtaining the growth stage information; according to the color parameter of each pixel point and the environment illumination information, performing color quality evaluation on each pixel point in the image data to obtain a color quality evaluation index; target pixel points with the color quality evaluation indexes lower than a preset threshold value are recognized between the plant main body area and the plant extension area, and a potential lesion area is constructed according to the recognized target pixel points. According to the method, through color quality evaluation, plant area identification and growth model simulation, a potential lesion area can be identified early, dynamic adjustment is carried out according to growth stage information, and the accuracy and timeliness of disease prediction are enhanced.

The invention relates to the technical field of medical health informatics, and discloses a tumor patient meridian energy dynamic monitoring system and method. The system comprises a midnight-noon ebb-flow time sequence energy mapping module, a multi-modal tumor characteristic signal acquisition module, a tumor focus-meridian correlation map construction module, a chemotherapy toxic reaction prediction module and a moxibustion intervention decision module. Dynamic and accurate monitoring of the meridian energy state of a tumor patient is achieved, potential risks can be early warned 12-24 hours in advance by establishing a chemotherapy toxicity risk scoring algorithm, the life quality of the patient is remarkably improved by generating a personalized moxibustion intervention scheme, and clinical decision support is provided for traditional Chinese and western medicine combined tumor auxiliary diagnosis and treatment.

The application discloses a cell detection method and system based on deep learning and machine vision, which comprises the following steps: cutting a cervical liquid-based cell pathology digital image into a plurality of sub-images to form a sub-image set; inputting the sub-image set into a normal cell detection model and a lesion cell detection model respectively, and identifying normal cells and lesion cells and their categories; selecting an overlapping area of the normal cells and the lesion cells, and performing secondary classification on the overlapping area through a classification model; performing threshold segmentation on granulocytes in the cervical liquid-based cell pathology digital image to obtain all possible granulocyte targets, filtering to determine final granulocyte targets, and counting and determining the number of the granulocytes. The application solves the problem that the detection model in the prior art has poor detection effect due to the imbalance of normal cell and lesion cell categories, improves the accuracy of cell identification, and realizes accurate detection and identification of cervical liquid-based cells in combination with accurately identified granulocytes.

The invention discloses a method and system for constructing a living fish underwater feature database and a medium, and the method comprises the steps: collecting original fish information through a preset frequency, carrying out the three-dimensional point cloud reconstruction of a second fish image obtained after preprocessing, and extracting the static phenotypic parameters, such as the scale arrangement features and fin ray morphological features, of the surface of a fish body; body surface texture reflection characteristics are obtained through multispectral analysis; meanwhile, associating time domain features of the second fish image and the second acoustic signal, extracting dynamic behavior features such as a motion trail and swimming bladder vibration frequency, and establishing a feature coding library containing typical behavior patterns; a mapping relation network of different disease types, body surface lesion area spatial distribution and behavior abnormal modes is constructed based on the features, and a feature parameter conversion relation is established; finally, various characteristic parameters are stored in a structured mode, a multi-dimensional characteristic database is formed, multi-dimensional correlation analysis of static phenotypes and dynamic behaviors of fishes is achieved, and the accuracy of disease diagnosis and cross-species characteristic migration is improved.

The invention discloses a magnetoencephalogram-based epilepsy lesion positioning method and system and a medium, and relates to the technical field of artificial intelligence, and the method comprises the steps: carrying out the preprocessing of a structure image of a patient, carrying out the registration with the magnetoencephalogram of the patient, carrying out the grid division of a cerebral cortex region based on the preprocessed structure image and a registration result, and obtaining a forward model of the patient; performing preprocessing and spine wave detection on the magnetoencephalogram to obtain a spine wave time point sequence; based on the forward model and the ratchet wave time point sequence, using a magnetic dipole algorithm to calculate a source coordinate and a source direction of a ratchet wave time point, and classifying the ratchet wave time point sequence according to the source coordinate and the source direction to obtain a clustering result; calculating the source coordinate and the source direction of the class center of each class in the clustering result by using a magnetic dipole algorithm; generating a clinical report of the patient; according to the positioning method, the problems of large epilepsy diagnosis difference and error proneness caused by level difference of different doctors are solved, and the epilepsy focus position can be quickly determined.