17 results about "Anatomical atlas" patented technology

The invention provides a gastroscope image recognition and auxiliary diagnosis system and method based on deep learning and large language model fusion, and the system comprises a data collection and processing module which is used for obtaining and preprocessing various types of gastroscope images; the gastroscope picture recognition and classification module is used for inputting the preprocessed gastroscope pictures into a GastroHAF model for training and outputting recognition and classification results of the gastroscope pictures, and the GastroHAF model comprises a weak supervision anatomical mark positioning sub-module, a space co-occurrence context reasoning sub-module and an anatomical atlas guided hierarchical classification sub-module; and the auxiliary diagnosis module is used for outputting stomach diagnosis results and examination suggestions based on the fine-tuned Chinese medical big language model. The GastroHAF model provided by the invention can quickly, effectively and accurately judge the position of the gastroscope in combination with prior anatomical knowledge, and can effectively assist doctors in stomach examination in combination with a large language model.

The application relates to the technical field of rehabilitation image processing, and provides a rehabilitation treatment dynamic digitalization auxiliary method based on a graphics algorithm and deep learning. The application aligns real-time collected local images with standard anatomical structures in a rehabilitation anatomical atlas library in high precision by constructing and training an image algorithm comparison deep learning model, matches the deep local anatomical tissues to a display terminal through a local image capture post-processing algorithm and a comparison image matching algorithm, so that a therapist can observe the deep local anatomical tissues in real time during operation, and the accuracy of anatomical positioning and the safety of treatment are improved. By constructing and training a rehabilitation clinical treatment algorithm matching learning model, combining collected clinical data and a rehabilitation clinical standard path knowledge base, rehabilitation diagnosis, rehabilitation treatment list preparation and associated anatomical image output are completed, and are synchronously output to a display terminal, so as to adapt to the operation needs of clinical dynamic precise rehabilitation.

The invention discloses an anatomical atlas-based image examination application interaction method and system and a storage medium, and the method comprises the steps: receiving patient information which comprises gender, medical history and examination type instructions; a corresponding three-dimensional anatomical atlas is dynamically generated according to the gender, and mutually exclusive organs in the male atlas and the female atlas are automatically hidden; displaying an anatomical structure in a graphical interface in a layered manner according to the three-dimensional anatomical atlas; dividing human body system modules according to inspection types, and displaying different human body system modules in different colors; responding to user interaction operation: clicking the selected check part for a single time to generate a selected mark; the selection is cancelled through double clicks, and the selection mark disappears; when multiple parts are selected at the same time, the system automatically detects conflicting items and pops up an alarm for the conflicting items; and S5, generating an electronic application form. According to the method, the image examination application error rate can be remarkably reduced, the working efficiency of doctors is greatly improved, and the clinical operation safety is enhanced.

The present invention discloses a system and method for guided lung coverage and automatic detection using an ultrasound device. The method for guided coverage and automatic pathology detection of a subject includes positioning an ultrasound probe on an area of the subject's body to be imaged. The method includes capturing a video of the subject and processing the video to generate a torso image of the subject and identifying the position of the ultrasound probe on the subject's body. The method includes aligning the video with an anatomical atlas to generate a mask of the area of the subject's body to be imaged and superimposing the mask on the torso image, the area including multiple sub-regions of the subject's body. The method also includes displaying an indicator corresponding to the position of each sub-region in the multiple sub-regions on the torso image. The method also includes displaying the relative position of the ultrasound probe relative to the indicator, the indicator corresponding to the position of each sub-region in the multiple sub-regions of the subject's body to be imaged.

This invention provides an injection path guidance method, system, device, and medium based on ultrasound and laser combined navigation, belonging to the field of medical injection technology. The method includes: denoising an initial sound wave to obtain a denoised wave; identifying the boundary points of the denoised wave based on the mean square relative fitting error to obtain an anatomical structure image of the target muscle; performing image segmentation on the anatomical structure image to obtain a target structure image of the target muscle; extracting feature information at different scales from the target structure image and then performing adaptive clustering through variable convolution to obtain a three-dimensional result of the target; registering and comparing the target three-dimensional result with an anatomical atlas database, marking key avoidance structures to determine a safe puncture boundary; determining the puncture target point and alternative paths in the target three-dimensional result based on the safe puncture boundary; and projecting light spot markers and the target path onto the target muscle using a near-infrared laser navigation module based on spatial transformation relationships between the puncture target point and the alternative paths.

The invention discloses a fracture reduction path planning system and method based on image data, and the method comprises the steps: carrying out the fine anatomical structure segmentation of high-resolution preoperative image data, firstly constructing a three-dimensional bone block model and a three-dimensional high-risk soft tissue model, carrying out the meshing of the three-dimensional bone block model and the three-dimensional high-risk soft tissue model based on anatomical map data, and carrying out the risk assignment, a predictive static probability risk field network is obtained; in the operation process, 2D-3D registration and tracking are conducted through intraoperative imaging data, real-time displacement information of a key tracking point is obtained, then the static probability risk field network is dynamically updated, and an updated probability risk field network capable of reflecting current soft tissue real deformation is formed; and finally, based on the updated risk field and the current pose of the robot, self-adaptive adjustment of a local path is carried out, so that a safe and efficient fracture reduction path is accurately planned. In this way, the precision and safety of the fracture reduction surgery are remarkably improved.

The present invention relates to a three-dimensional biological image deformation method based on local and global joint constraints, comprising: obtaining a global matching point set; calculating local constraints based on label index information ind; calculating global constraints; calculating a downsampled displacement field DF based on the local and global constraints; calculating a cubic B-spline basis function matrix; obtaining a final generated displacement field DF_whole; and performing three-dimensional biological image deformation to obtain a deformed three-dimensional biological image. The present invention utilizes a biological image anatomical atlas to calculate the downsampled displacement field with local and global joint constraints, and interpolates and smoothes the downsampled displacement field blocks by sliding the influence area of ​​the cubic B-spline basis function matrix to obtain the final displacement field and perform three-dimensional biological image deformation. The present invention generates a smooth displacement field that links the local and global components, which can effectively improve the accuracy of local deformation during biological image deformation and registration, while also achieving a smooth overall deformation effect.

The application relates to a multi-region identification method, device and equipment of an endoscope image and a storage medium, wherein the multi-region identification method of the endoscope image comprises the following steps: projecting a three-dimensional anatomical atlas matched with an endoscope image to the endoscope image, and generating a region mask of the endoscope image according to a projection result; wherein the region mask is used for indicating an anatomical region corresponding to each pixel position in the endoscope image; based on the region mask, a constraint mask of each anatomical region is generated; based on a first image feature of the endoscope image and the region mask, a target image feature of the endoscope image is determined; the target image feature is enhanced based on the constraint mask of each anatomical region, and region identification is performed on the endoscope image based on the enhanced target image feature. Through the application, the problem that accurate identification of multiple anatomical regions in an endoscope image is difficult to realize is solved, and accurate identification of multiple anatomical regions in an endoscope image is realized.

The invention belongs to the technical field of biological tissue sample dyeing and three-dimensional imaging, and particularly relates to an anti-reflection method and reagent suitable for rapid marking of complete organ cell construction. The anti-reflection dyeing reagent provided by the invention comprises a composite anti-reflection agent, a dyeing agent and a solvent, and the composite anti-reflection agent comprises a detergent, a super-hydrating agent and a cholesterol remover, so that a cell nucleus dye and a biomacromolecule fluorescence coupling marker can effectively mark a complete organ; and the staining time of the complete mouse brain cell construction can be shortened from 3-4 weeks to 5 days in a passive soaking manner. According to the anti-reflection method based on the reagent, complete organ cell construction marking can be rapidly achieved in a high-quality mode only through a passive soaking mode, and the method has the advantages of being easy and convenient to operate, high in universality, short in dyeing time, high in uniformity, high in signal-to-background ratio and the like; the method is suitable for three-dimensional reconstruction space positioning, cell counting and morphological research in physiological and pathological research, accurate anatomical atlas drawing and the like.

The application provides an AI intelligent injury classification method and system based on visualization and big data, relates to the technical field of medical first aid, and comprises receiving spatial markers of rescue personnel on a standardized human body anatomical atlas and physiological data of a patient, extracting spatial features and constructing a multi-modal feature set. A trained classification model is used to output injury grade prediction results and confidence, and a digital injury label with geographical information is generated and bound accordingly, and is transmitted in real time to a command platform. Finally, a casualty distribution heat map is generated based on the labels aggregated by the platform, and a resource scheduling priority and allocation suggestion are generated in combination with a medical resource matching relationship. The application realizes the standardization, intelligentization and visualization of injury classification, and improves the efficiency and accuracy of rescue resource scheduling in large-scale casualty incidents.

The invention relates to a multi-region recognition method, device and equipment for an endoscope image and a storage medium, and the method comprises the steps: projecting a three-dimensional anatomical atlas matched with the endoscope image to the endoscope image, and generating a region mask of the endoscope image according to a projection result; wherein the region mask is used for indicating an anatomical region corresponding to each pixel position in the endoscope image; generating a constraint mask of each anatomical region based on the region masks; determining a target image feature of the endoscope image based on the first image feature of the endoscope image and the region mask; and enhancing the features of the target image based on the constraint mask of each anatomical region, and performing region identification on the endoscope image based on the enhanced features of the target image. Through the method and the device, the problem that accurate recognition of multiple anatomical regions in the endoscope image is difficult to realize is solved, and accurate recognition of the multiple anatomical regions in the endoscope image is realized.

Systems and methods for patellofemoral preparation are disclosed herein. A method may include receiving patient imagery of a patient's anatomy comprising a knee joint; registering the patient imagery to at least one of a pre-existing anatomical atlas or a three-dimensional model generated from the patient imagery; determining a location of a native femoral trochlear groove of a femur based on the registered patient imagery; determining the location of an implanted femoral trochlear groove from a three-dimensional model comprising a planned modification of the registered patient imagery and an affixed implant comprising femoral implant component; comparing native groove and the implant groove to assess congruence between the patient's anatomy and the implant; and generating a recommendation to modify at least one of a placement of a patella of the knee joint, a surface of the patella, and an attribute of the femoral implant component based on the comparison.

To provide a system and method for real-time planning and monitoring of cardiac ablation using an anatomical map.SOLUTION: A method includes receiving an anatomical map of wall tissue of at least a portion of a ventricle, the map overlaid with a grid of ablation tags that are graphically encoded according to respective levels of ablation of the wall tissue. Upon placing a multi-electrode ablation catheter in the vicinity of the wall tissue, one or more of the ablation tags are graphically re-encoded according to (i) existing levels of ablation associated with the tags and (ii) electrode proximity to wall tissue locations associated with the tags. The anatomical map, having the re-encoded ablation tags, is displayed to a user.SELECTED DRAWING: Figure 1

The invention discloses a tumor recurrence and metastasis risk prediction method and system based on an anatomical map. The method comprises the following steps: acquiring a patient image report, a complaint text and non-equidistant tumor marker data; based on a tumor metastasis knowledge graph, mapping an image report and a chief complaint text to corresponding anatomical nodes, calculating semantic alignment weights of objective lesions and subjective symptoms on the nodes by using a cross attention mechanism, and generating multi-modal fusion node features; utilizing a continuous time model to extract biochemical trend characteristics of the marker data as a global state variable injection map; and finally, inputting the multi-modal fusion node features and the global state variables into a graph neural network for feature aggregation and reasoning, and outputting a risk prediction result and a high-risk anatomical region. According to the invention, early-stage accurate early warning and interpretable path reasoning of tumor recurrence and metastasis risks are realized.

The application discloses a tumor recurrence and metastasis risk prediction method and system based on an anatomical atlas, and the method comprises the following steps: acquiring a patient image report, a chief complaint text and non-equidistant tumor marker data; based on a tumor metastasis knowledge graph, the image report and the chief complaint text are mapped to corresponding anatomical nodes, the semantic alignment weight of objective lesions and subjective symptoms on the nodes is calculated by using a cross-attention mechanism, and multi-modal fusion node features are generated; the biochemical trend features of the marker data are extracted as global state variables by using a continuous time model to inject the graph; finally, the multi-modal fusion node features and the global state variables are input into a graph neural network for feature aggregation and reasoning, and a risk prediction result and a high-risk anatomical region are output. The application realizes early and accurate early warning and an interpretable path reasoning for tumor recurrence and metastasis risk.

The application discloses a pain positioning and auxiliary diagnosis method and system based on a three-dimensional human body model marking. Firstly, a three-dimensional human body model is constructed, human body parts are manually marked according to an anatomical atlas, a mapping file of a surface patch ID and a part field is generated, and 30 spinal nerve dermatomes are associated with the surface patch. The patient marks the pain area on the model, the system obtains the selected surface patch ID set, converts it into a human body part and a dermatome field by using a reverse index. Combined with the pain type and the accompanying symptoms, vector semantic retrieval and structured matching are carried out in the muscle fascia, spinal disease and fourteen meridian three major theoretical medical knowledge bases to obtain relevant medical knowledge. Finally, a diagnosis suggestion containing a suspected disease, diagnosis analysis, treatment suggestion and recommended department is generated by a large language model. The application realizes the visualization and intelligentization of outpatient pain marking, greatly shortens the positioning time of the first diagnosis, significantly improves the positioning accuracy, and then significantly improves the diagnosis and treatment efficiency.

The invention relates to the technical field of ultrasonic diagnosis, in particular to an abdominal ultrasonic multi-modal image fusion analysis system which comprises a multi-modal space alignment module, an anatomical semantic structuring module, a multi-modal feature fusion and visualization module, a multi-parameter quantitative analysis module, a qualitative evaluation matrix construction module and an intelligent report generation module. By taking the gray-scale ultrasound image sequence of the target abdominal region as a space reference, aligning the elastography and ultrasound contrast sequences to obtain a multi-modal image set; mapping an anatomical structure, tissue hardness and blood perfusion information in the image set to a standard anatomical map to generate structured data; associating and visually coding the tissue hardness distribution information and the blood perfusion dynamic information to obtain a fused image; feature parameters of the fused image are analyzed and compared with a clinical threshold value to obtain quantitative parameters, and a qualitative evaluation matrix is constructed; summarizing qualitative evaluation indexes, quantitative parameters and structured description data to generate an analysis report; the efficiency of abdominal ultrasonic diagnosis analysis can be improved.