77 results about "Disease category" patented technology

The invention relates to the technical field of road detection, in particular to an intelligent road disease detection method and system based on a three-dimensional ground penetrating radar, and the method comprises the steps: obtaining and processing three-dimensional radar data, and obtaining a horizontal section image in the depth direction and vertical section images of a plurality of channels in the measuring line direction; determining the boundary position of the underground structure layer; selecting a horizontal slice image with a corresponding depth according to the boundary position, and inputting the horizontal slice image into a first disease detection model to obtain a preliminary disease candidate area; mapping the preliminary candidate region to a vertical profile image, intercepting a local vertical profile image of each channel, and inputting the local vertical profile image into a second disease detection model to obtain disease category information; fusion decision is carried out based on the transverse position of the candidate area and the disease category information of each channel, a final disease type is determined and is associated to the candidate area, consistency of disease positioning and type judgment is realized through cooperative utilization of the horizontal section image and the multi-channel vertical section image, and the accuracy and stability of detection are improved.

The invention discloses an unmanned aerial vehicle road disease detection and analysis system and method based on a YOLO algorithm, and the method comprises the following steps: synchronously collecting a road image and geographic coordinates through an unmanned aerial vehicle, and constructing an image data set with geographic reference; constructing an initial YOLO target detection model based on the data set; introducing an additional detection layer for detecting a pixel area into the model, and embedding a channel attention mechanism into the feature extraction network to obtain an improved YOLO target detection model; reasoning a data set by using the model, and outputting a disease category, a bounding box coordinate and a confidence coefficient; pixel coordinates are converted into geographic coordinates through a coordinate conversion algorithm, and disease records with accurate geographic coordinates are generated; and optimizing and updating the model based on the record as an incremental training sample. According to the method, the disease detection precision and the small target identification capability are effectively improved, and the long-term adaptability and generalization performance of the model are enhanced through a closed-loop incremental learning mechanism.

The invention belongs to the technical field of underground pipeline detection, and discloses an underground pipeline CCTV camera auxiliary control method and device based on deep learning, and the method comprises the steps: firstly obtaining continuous real-time image frames, and obtaining the results of a disease type, detection confidence, a detection frame position and the like through a pipeline disease object detection model; starting tracking after a disease is detected for the first time, associating subsequent frame results according to a category consistency and position similarity rule, and constructing a continuous frame detection result set; based on the set, time stability and space stability are judged in sequence, and control-level confirmable diseases are screened out; and calculating an effective shooting angle interval by combining the transverse coordinate distribution range of the detection frame and the field angle parameter of the camera, and finally controlling the camera to execute rotary shooting in the interval. The method can reduce the false triggering rate, improve the disease imaging quality and detection efficiency, reduce the manual dependence and guarantee the reliability of the detection result.

The present application relates to the technical field of image processing, in particular to a kind of agricultural disease detection method based on multi-scale feature extraction, comprising: obtaining target disease image, according to the mode of ladder convolution processing, the hierarchical branch of target disease image is constructed, under any hierarchical branch, with the mode of each level series coupling, determine the local disease feature of target disease image;Local disease feature is extracted by channel attention, and the local disease feature after attention recalibration is obtained;Local disease feature is mapped into semantic sequence space, and local disease feature is spatially attenuated and weighted to determine the disease distribution characteristics of crop disease under multi-scale fusion;At least one disease category is obtained based on the spatial position corresponding to disease distribution characteristics, and the average time and average accuracy of disease detection are combined to determine the disease detection effect.The precision and efficiency of disease identification are improved.

The invention relates to the technical field of skin disease classification, in particular to an auxiliary skin disease classification method and system based on multi-modal medical data, and the method comprises the steps: extracting features of a plurality of types of first data, and obtaining a plurality of initial feature vectors; performing low-level fusion and high-level fusion according to the plurality of initial feature vectors to obtain a comprehensive feature vector, inputting the comprehensive feature vector into a classifier, and determining a predicted skin disease category; and generating a diagnosis report according to the predicted skin disease category. According to the invention, low-level fusion and high-level fusion are carried out according to the plurality of initial feature vectors to obtain the comprehensive feature vector, and the predicted skin disease category is determined by fusing the data of the plurality of categories of the skin diseases and inputting the comprehensive feature vector into the classifier, so that the accuracy of skin disease classification is improved.

The present disclosure relates to a data model establishing method and device, and a clinical auxiliary decision method and device. The data model establishing method comprises: field disassembling historical data according to different disease categories; structured processing is performed according to the fields obtained by disassembling to form a structured output rule; and a disease data model is established according to the structured output rule combined with clinical data. The present disclosure also relates to a data model establishing device, an electronic device and a computer readable medium, and a clinical auxiliary decision method, device, electronic device and computer readable medium based on the data model establishing method. The structured output rule is generated by structured processing of diseases, and the clinical data is saved in a relational structure in a database according to the rule to form a data model, so that the clinical data can be effectively utilized, the interconnection and intercommunication between data can be realized, and the research conversion rate can be improved.

The application discloses an information processing method and device for medical image classification, equipment and medium, relates to the technical field of image recognition, and comprises the following steps: dividing a plurality of preset disease categories into a preset head category and a preset tail category; clustering each preset disease category in the preset tail category into a plurality of abnormal disease categories, and determining third training data corresponding to each abnormal disease category based on second training data corresponding to each preset disease category in each abnormal disease category; determining a target data set based on the first training data, the preset disease category corresponding to the first training data, the third training data, and the abnormal disease category corresponding to the third training data; training an initial classification model based on the target data set to obtain a target classification model, and generating a target disease classification result of an initial medical image to be recognized by using the target classification model. The application can efficiently process long-tail distribution data of medical images, and improve the recognition accuracy and reliability of rare diseases.

The invention provides an expressway foreground image disease detection method and system, and relates to the technical field of expressway disease detection, and the method comprises the steps: obtaining an expressway foreground image, carrying out the recognition according to a preset neural network model to obtain a disease region and a disease type, and generating a Grad-CAM thermodynamic diagram for the disease region through a Grad-CAM technology; performing grid division on the Grad-CAM thermodynamic diagram containing the disease area to obtain standard detection frames, and counting the proportion of abnormal pixels in each standard detection frame; judging whether the abnormal pixel proportion exceeds an abnormal threshold value or not; if yes, the disease area in the standard detection frame is an effective disease area, the accurate boundary of the effective disease area is drawn to quantify the disease size, the disease position and the disease number of the expressway foreground image are obtained according to the accurate boundary, and disease detection is achieved in combination with the disease category. According to the invention, the detection convenience, the identification precision and the size standardization are improved.

The invention discloses a disease identification method, device and system, and a storage medium, and the method comprises the steps: inputting a to-be-identified disease image, and sequentially extracting the deep and shallow features of the to-be-identified disease image through a multi-layer feature extraction module; generating hierarchical prototypes of corresponding categories in different depth feature spaces, and fusing the hierarchical prototypes to form a comprehensive prototype; performing prototype classification reasoning based on the comprehensive prototype and a learnable measurement mechanism, and outputting disease categories; in the training process, the distinction degree between prototypes is enhanced by introducing prototype separation constraints; in the incremental learning stage, an original prototype of a new category sample is finely adjusted by adopting an elastic prototype updating strategy, a category prototype is newly added by utilizing a prototype classifier expansion strategy, and the old category recognition performance is ensured not to be lost. By adopting the technical scheme of the invention, similar category confusion can be effectively inhibited, and the accuracy and robustness of disease identification under a small sample condition are improved.

The present application relates to the technical field of computer vision and artificial intelligence, and particularly discloses a neural network optimization method based on a visual state space model for bridge diseases, which comprises the following steps: constructing a neural network comprising a feature extraction backbone network and a task adaptation head network, modeling the image feature sequence based on the visual state space model to capture local details and long-distance global dependencies, and using the task adaptation head network to output disease categories, confidence and positions; training the model using a standardized data set, dynamically optimizing by evaluating neuron importance, sorting and cutting redundant neurons; inputting the preprocessed image to be detected into the optimized model, performing feature extraction, multi-branch processing and non-maximum suppression, and outputting accurate disease recognition results. The present application improves disease feature extraction accuracy, realizes model lightweight, adapts to multi-scale disease detection, enhances the practicality of recognition results, and is suitable for intelligent bridge disease detection scenarios.

The present disclosure provides biomarker screening model training method and device, method and device, network, equipment and medium, and relates to the technical field of image processing. The implementation scheme of the present disclosure is: a heterogeneous graph construction module, configured to convert an obtained target data set into a heterogeneous graph structure; a double-flow graph convolution network module, wherein a protein interaction flow network is configured to output a first graph-level feature based on a first adjacency matrix; a gene regulation flow network is configured to output a second graph-level feature based on a second adjacency matrix; an attention fusion classification module is configured to weight and fuse the first graph-level feature and the second graph-level feature, and input the fused feature into a classifier to obtain a prediction probability value for a target disease category; and an explainable attribution module is configured to integrate a gradient along a path from a baseline input to an actual input, quantify a contribution score of each protein node feature in the heterogeneous graph structure to the prediction probability value, and output a candidate biomarker combination according to the contribution score.

The application discloses a kind of light-weight model and attention mechanism pest detection model and training method, belong to deep learning technical field.The model is based on YOLOv8-Seg architecture, by introducing light-weight MobileViT main network instead of original CSPDarknet53, combined with global feature fusion module and coordinate attention mechanism, while reducing parameter quantity and computational complexity, the feature expression ability is enhanced;In neck network, replace the original FPN structure with bidirectional feature pyramid network, fully excavate multi-scale feature and context information, optimize multi-scale feature fusion.Model combines the segmentation ability of SAM2 with the target detection ability of YOLO-SEG, shape adaptive labeling is realized, and the influence of complex background on detection accuracy is effectively shielded.mAP@[0.5:0.95] is stabilized at 0.8-0.9, and the balance of each disease category precision and recall rate index is good.

Quantum entanglement neuro morphology bridge disease holographic monitoring repair method and system: deploy quantum entanglement sensor array to obtain micro-disease information and fuse infrared sensor, laser radar, industrial camera data, encrypt transmission preprocessing through quantum communication network to generate fusion feature vector, disease category probability, severity score and comprehensive risk index; build bridge three-dimensional coordinate system to reconstruct three-dimensional geometric model, map the index to three-dimensional coordinate system, output three-dimensional disease holographic model through spatial clustering; weighted sum of comprehensive risk index, average severity, structure and traffic importance weight to get repair priority score and sort, under the constraint of cost and construction period, take repair cost, time, risk reduction and life increment as the comprehensive optimization objective, solve the construction control parameter and dynamically evaluate the repair quality to generate structured repair record; continuously collect monitoring data to calculate health indicators, establish degradation model to determine failure probability and remaining life, form maintenance plan and update parameters.

The present application relates to the technical field of pathological image classification, in particular to an intestinal mucosa tissue pathological image classification method and system based on artificial intelligence. The present application selects a histopathological region from a suspected pathological region, divides a sequence obtained by sequentially arranging the histopathological region into different subsequences, acquires pathological feature templates of the subsequences under each disease category, determines the disease category to which the histopathological region in the subsequence belongs according to the similarity between the texture distribution, blood vessel distribution characteristics of the histopathological region in the subsequence and the pathological feature templates, and acquires the feature templates of each subsequence under each disease category according to the pathological features of the histopathological region belonging to the same disease category and the pathological feature templates of the previous subsequence of each subsequence under each disease category. The present application realizes gradual and accurate matching of the pathological feature templates through dynamic and iterative optimization of the feature templates with the subsequences, and increases the accuracy of pathological feature matching of the intestinal mucosa pathological position.

The invention relates to the technical field of image recognition, in particular to a silkworm disease recognition system which comprises an image gray analysis module, a self-adaptive image enhancement module, a multi-dimensional feature extraction module, a feature saliency evaluation module, a dynamic weight distribution module and a disease classification mapping module. Identifying an overall gray level distribution condition and a local gray level fluctuation condition in the original image data of the target silkworm body to determine a dynamic adjustment parameter, and correcting the original image data to obtain enhanced image data; integrating multi-dimensional feature information in the enhanced image data into silkworm body state feature information; judging the significance degree of different types of information in the silkworm body state characteristic information for distinguishing different diseases so as to allocate the emphasis proportion of the characteristic information in the silkworm body state characteristic information; fusing the emphasis proportion and the silkworm body state feature information, and mapping the fused silkworm body state feature information to a preset silkworm disease feature template library to obtain disease categories; according to the invention, the accuracy of silkworm disease recognition can be improved.

The application discloses a railway track disease detection method based on coordinate attention, comprising the following steps: acquiring a railway track image, performing adaptive pyramid scaling and normalization processing, and expanding a data set based on a Mosaic data enhancement method; adopting a lightweight backbone network based on FasterNet to extract multi-scale features of the railway track image; strengthening disease area related channel features based on an MSCAM multi-scale convolution attention module; connecting a coordinate attention CoordAtt module after the output of the MSCAM multi-scale convolution attention module to form a fused feature enhancement module, and obtaining disease area related channel features after association; fusing a perception loss on the basis of an original loss function of YOLOv8 to form a joint loss function, optimizing disease texture alignment in a deep disease area feature space, and forming enhanced features; inputting the features into a detection head to output disease categories, a bounding box and a confidence, and completing railway track disease detection. The application also discloses a system, an electronic device and a computer readable storage medium.

The invention relates to the technical field of pathological image classification, in particular to an intestinal mucosa tissue pathological image classification method and system based on artificial intelligence. The method comprises the following steps: selecting histopathological regions from suspected pathological regions, and dividing a sequence obtained by sequentially arranging the histopathological regions into different subsequences; acquiring a pathological feature template of the sub-sequence under each disease category, and determining the disease category to which the tissue pathological area in the sub-sequence belongs according to the similarity between the texture distribution and blood vessel distribution features of the tissue pathological area in the sub-sequence and the pathological feature template; and according to the pathological feature template of the previous sub-sequence of each sub-sequence under each disease category and the pathological features of the histopathological region belonging to the same disease category, obtaining the feature template of each sub-sequence in each disease category. According to the method, through dynamic iterative optimization of the feature templates along with the subsequences, progressive accurate matching of the pathological feature templates is realized, and the accuracy of pathological feature matching of the pathological positions of the intestinal mucosa is increased.

The invention discloses a critical patient analgesic drug dose dynamic regulation and control system based on reinforcement learning, and relates to the technical field of reinforcement learning. The system comprises a data acquisition module used for acquiring first patient information of a target critical patient, the first patient information comprising invariant intrinsic information, disease category information and real-time physiological information; the state mapping module is used for constructing a state mapping model in combination with a reinforcement learning method according to the first patient information, inputting the real-time physiological information to the state mapping model, and obtaining pseudo standard physiological information of a target critical patient; and the regulation and control decision module is used for generating a suggested dose instruction for the analgesic drug according to a preset dose regulation and control rule based on the pseudo standard physiological information. According to the invention, the safety of the dosage of the analgesic drug and the generalization ability among different critical diseases are effectively improved.

The present application relates to the technical field of computer vision and road detection, and particularly relates to a pavement disease identification method, system, device and medium based on semi-supervised learning. The method comprises: processing a pavement image through an image recognition model to obtain an identification result containing disease category and spatial position information; based on the identification result, quantifying a disease area according to a grid of a preset size to obtain a quantification result; based on the identification result and the quantification result, generating a structured data file; in response to a review operation on disease data in the structured data file, correcting the disease data based on a user interaction instruction to obtain corrected disease data; and based on a data set containing the corrected disease data, iteratively training the image recognition model. Compared with the prior art, the present application effectively closes the loop between the manual review and correction link and the model training link, so that the model can be iteratively optimized using continuously generated correction data to realize self-evolution of performance.

The present invention provides a full-stack medical imaging foundation model, re for performing medical image segmentation, classification and localization using a unified language-image correlation mechanism. The present invention leverages pretrained language-guided associations to automatically recognize and localize disease targets without requiring medical imaging knowledge or manual box-prompting. The invention enables comprehensive clinical tasks across multiple disease classes and various medical imaging techniques, improves segmentation efficiency, and reduces human input burden. With operability through human language-only prompts by non-radiology specialists, the present invention improves real-world applicability and enables deployment of foundation model-based segmentation in diverse clinical environments.

The invention discloses a medical data association rule confidence degree dynamic updating system, and relates to the field of machine learning. The system comprises a rule monitoring module, a confidence coefficient updating module and a rule base management module, wherein the rule monitoring module obtains a symptom set and a labeling result and retrieves a matched target association rule in a rule base; the confidence coefficient updating module determines a time sequence attenuation parameter according to the disease category, and performs attenuation calculation on the pre-stored confidence coefficient in combination with a time interval from the last verification timestamp to obtain a basic confidence coefficient; if the labeling result is consistent with the rule, judging that the evidence is a forward evidence, updating the timestamp, and improving the confidence coefficient by using a forward enhancement strategy; if not, negative evidence is judged, counting is accumulated, and when the counting reaches a threshold value in a preset time window, the confidence coefficient is reduced based on a negative punishment strategy; and the rule base management module writes the updated new confidence into the rule base. By implementing the technical scheme provided by the invention, the accuracy of medical diagnosis is improved.

The invention relates to a multi-modal image fusion method and system and computer equipment, and the method comprises the steps: obtaining an sMRI image and an FDG PET image of a tested object, and carrying out the preprocessing of the sMRI image and the FDG PET image; calculating image entropies of all axial slices for each sMRI image, extracting a preset number of axial slices with the maximum image entropies as sMRI key slices, and extracting FDG PET key slices of the FDG PET image corresponding to the sMRI key slices; the sMRI key slices and the corresponding FDG PET key slices are fused, a fused image is obtained, and the fused image is used for recognizing the disease category to which the image belongs. According to the method and the device, more efficient and accurate recognition of people in different cognitive states is realized based on complementary information of sMRI and FDG PET modal images.

The application discloses a kind of based on the design method of structured report template of semasiology association, comprising the following steps: step S1, based on historical medical record big data semantics construction obtains first diagnosis and treatment knowledge graph;Step S2, based on the construction of second diagnosis and treatment knowledge graph of disease diagnosis and treatment guideline big data;Step S3, the first diagnosis and treatment knowledge graph and second diagnosis and treatment knowledge graph are fused to obtain the diagnosis and treatment structured knowledge graph of fusion representation diagnosis and treatment practical experience and diagnosis and treatment expert experience, and based on diagnosis and treatment structured knowledge graph constructs structured report template for disease category;Step S4, according to structured report template, uniform diagnosis and treatment is carried out to disease category to improve diagnosis and treatment standardization.The application makes it in accordance with structured report template to carry out disease diagnosis and treatment, that is, it is in accordance with diagnosis and treatment practical experience of doctor also in accordance with diagnosis and treatment expert experience, realizes diagnosis and treatment standardization and maneuverability, breaks through the limitation that computer-aided diagnosis method only uses diagnosis and treatment guideline driving.

The invention discloses a skin disease diagnosis method based on diffusion model data expansion, and relates to the technical field of medical image processing, and the method comprises the steps: obtaining skin disease image data, and carrying out the preprocessing of the collected skin disease image data, and obtaining an original data set; training the diffusion model by using the original data set; forming an extended data set by using the trained diffusion model; training the ResNet50 deep convolutional network by using the extended data set and optimizing parameters to obtain a diagnosis model of the skin disease; evaluating the trained diagnosis model by using an independent test data set, and improving the accuracy and robustness of the model by adjusting model parameters and an optimization strategy; and deploying the optimized diagnosis model into a diagnosis system, and after a user inputs a skin disease image, automatically outputting a diagnosis result and disease category classification by the system. Diversified skin disease composite image expansion training data are generated through the diffusion model, and the accuracy and robustness of skin disease diagnosis are improved in combination with the deep learning classification model.

This invention provides a full-stack medical imaging foundation model for performing medical image segmentation, classification, and localization using a unified language-image correlation mechanism. This invention leverages pre-trained language-guided associations to automatically identify and localize disease targets without requiring medical imaging knowledge or manual bounding box prompts. This invention enables comprehensive clinical tasks across multiple disease categories and various medical imaging techniques, improving segmentation efficiency and reducing the burden of manual input. By utilizing the operability of plain text prompts from non-radiologists, this invention improves real-world applicability and enables the deployment of foundation model-based segmentation in diverse clinical settings.

The invention discloses a radiology report generation method and system based on focus guide mask and knowledge graph enhancement, and belongs to the technical field of medical artificial intelligence. The method comprises the following steps: preprocessing a chest medical image and extracting local features; constructing a lesion knowledge graph containing an organ-lesion-disease category triple; obtaining a candidate organ and a mask image thereof through a pre-trained focus detection model; retrieving related knowledge from the knowledge graph based on the candidate organs to generate focus enhanced knowledge features, and inputting the organ mask and the original image into a mask image attention layer together to obtain mask enhanced image features; using a multi-branch gating cross-modal fusion module to carry out adaptive weighted fusion on the two types of features to obtain knowledge mask enhanced fusion representation; and finally, a radiology report is generated through a Transform encoder-decoder. According to the method, image-text alignment of organ granularity can be realized, language illusion in a generated report is effectively reduced, and clinical consistency and interpretability of the report are improved.

The application relates to the field of disease category analysis, and discloses a brain disease category analysis method based on magnetic resonance, which comprises the following steps: performing image preprocessing on a magnetic resonance brain image of a brain patient to obtain a preprocessed image; calculating the brain tissue surface area of the brain patient and determining the brain tissue shape of the brain patient; identifying the brain tissue features of the brain patient, performing wavelet coefficient decomposition, and obtaining different frequency subband coefficients of the brain tissue features; calculating the statistical features of the different frequency subband coefficients, constructing a feature vector of the statistical features based on the statistical features, performing brain disease analysis on the brain patient, and obtaining a preliminary disease analysis category; extracting the texture features of the preprocessed image, performing feature fusion on the texture features and the feature vector, obtaining fused features, and performing accuracy analysis on the preliminary disease analysis category; and when the accuracy analysis result is optimal, constructing a disease analysis report. The application can improve the accuracy of brain disease category analysis.

The present application relates to the technical field of computer vision and road detection, and particularly relates to a pavement disease identification method, system, device and medium based on semi-supervised learning. The method comprises: processing a pavement image through an image recognition model to obtain an identification result containing disease category and spatial position information; quantifying a disease area according to a grid of a preset size based on the identification result to obtain a quantification result; generating a structured data file based on the identification result and the quantification result; in response to a review operation on disease data in the structured data file, correcting the disease data based on a user interaction instruction to obtain corrected disease data; and iteratively training the image recognition model based on a data set containing the corrected disease data. Compared with the prior art, the present application effectively closes the loop between the manual review and correction link and the model training link, so that the model can be iteratively optimized using continuously generated correction data to realize self-evolution of performance.

The application discloses a road disease YOLO detection system and method based on a lightweight CNN, and particularly relates to the technical field of computer vision, acquires a road surface image frame and inputs the YOLO detection model based on the lightweight CNN, outputs a disease detection result set, and generates a disease observation record sequence containing a timestamp, a spatial position, a disease category, a confidence score, an event size representation quantity and an observation weight; spatial correlation and aggregation are performed based on the sequence, an event-level disease object is constructed, and an event evidence consistency credibility comprehensive quantity is generated based on the consistency of multiple observations; based on the event-level disease object, the severity of the event, the evolution trend, the road segment attribute and the maintenance resource state information are fused, the credibility comprehensive quantity is taken as a gating item, and the resource cost is taken as a penalty item, so that the urgency and the resource benefit comprehensive quantity are calculated, a work order generation request package is output, and deduplication dispatching and state closed-loop backfilling are performed based on the work order state and a disposal receipt.