34 results about "Computer-aided diagnosis" patented technology

This invention relates to a grading method for diabetic retinopathy based on a local-global interactive dual-branch network, belonging to the fields of deep learning, medical image analysis, and computer-aided diagnosis. It includes: inputting the generated initial feature sequence into a global scanning module; using dilated reparameterized convolution to capture multi-scale structural prior information; inputting the feature map with structural prior information into a core dual-branch LoGo module; the local flow extracting fine-grained lesion features through depthwise separable convolution; the global flow generating spatially variable convolution kernels based on the global context through contextual hybrid dynamic convolution; and performing bidirectional cross-modulation through an adaptive multi-scale feature interaction aggregation module to sharpen local details for global semantics and filter local noise from the global context, ultimately outputting a disease severity grade. This invention explicitly simulates the cognitive strategies of clinicians, significantly improving grading accuracy while maintaining computational efficiency.

This invention discloses a multi-label classification method for medical images based on spatiotemporal integration and adaptive normalization, belonging to the field of medical image processing and computer-aided diagnosis technology. The invention proposes an improved scheme. Firstly, it constructs a dynamically balanced data input stream through frequency inverse sampling and cosine annealing strategies. Secondly, it introduces group normalization to replace batch normalization in the feature extraction network, solving the training convergence problem under limited GPU memory. During training, it employs a focal loss function to mine hard-to-classify samples. In the inference stage, the invention constructs a spatiotemporal integration mechanism based on multi-view space transformation and multi-stage model weight fusion, combined with an adaptive threshold decision algorithm based on maximizing F1 scores to output diagnostic results. This invention effectively improves the recognition accuracy of key pathological features such as cardiac hypertrophy and edema, while significantly improving the recall rate of small lesions, exhibiting high robustness and clinical auxiliary value.

The application relates to a light wavelet enhancement fusion medical image segmentation method, and belongs to the technical field of medical image processing and computer-aided diagnosis. The core of the method is to construct a light WEF-Net network, which comprises an encoder, a bottleneck layer and a decoder. The encoder adopts a dual-domain perception module, extracts complementary features from the frequency domain and the time domain through wavelet transformation and convolution, and simultaneously extracts complementary features from the frequency domain and the time domain. The bottleneck layer is designed with a feature aggregation Kolmogorov-Arnold transformation module, which is used for efficiently fusing multi-scale semantic information and enhancing the nonlinear modeling capability. The network level also integrates a sawtooth rolling feature fusion module, which enhances the global continuity of the features through the channel rolling and spatial scanning mechanism to improve the integrity of the boundary segmentation. Experiments show that the method realizes excellent performance on multiple public medical image datasets, while maintaining low parameter quantity and low computational quantity, and significantly improves the segmentation precision.

The application relates to a chronic kidney disease prediction method based on clinical information graph representation, belongs to the technical field of computer-aided diagnosis of chronic kidney disease (CKD), and aims to solve the problem of missed diagnosis caused by the fact that the kidney function index of early CKD is not obvious. The incidence of CKD is high, the early symptoms are hidden, and the disease is easy to be missed, thus developing into end-stage renal disease. Therefore, the application provides a chronic kidney disease prediction method based on clinical information graph representation. The method first extracts fundus image and clinical index features; the clinical index is fused into a clinical index joint feature through text embedding and numerical feature fusion, and the joint feature is fused with the fundus image feature through cross-modal attention; the similarity between subjects is calculated based on the fused feature, and a subject relationship graph is constructed by using an adaptive dynamic threshold mechanism; finally, a hybrid graph neural network is used for graph representation learning, pathological similarity between subjects is mined, and accurate prediction of chronic kidney disease is realized. The application can improve the detection rate of early CKD and is applied to non-invasive early screening and risk early warning.

A computer-implemented diagnostic-assistance system for medical applications, comprises: an artificial intelligence neural network configured to classify images of an obtained image dataset according to a set of classes; a confidence module configured to generate a confidence measure associated with each of the classified images; a tagging module configured to generate, for the patient, a diagnostic signal based on the generated confidence measures associated with the classified images, wherein the diagnostic signal for the patient is tagged as conclusive if a processed combination of the confidence measures fulfills a condition and tagged as inconclusive if the processed combination of the confidence measures does not fulfill the condition; and an output interface configured to output the diagnostic signal, wherein if the diagnostic signal is conclusive the classification result is released, and if the diagnostic signal is inconclusive an additional diagnostic analysis is triggered.

The application discloses a skeleton quality driven tubular structure segmentation closed loop optimization method and system, which is applied to the technical field of biomedical image processing and computer aided diagnosis, and the method comprises the following steps: using a trained segmentation model to infer medical volume data to obtain a segmentation mask; skeletonizing the segmentation mask to extract a skeleton graph; performing topological defect detection on the skeleton graph to obtain a structured defect report; reversely mapping three-dimensional coordinates in the report back to a voxel space, taking each defect point as a center, a preset radius as a range, and generating a defect density weight graph according to a severity score; and using the weight graph as a spatial weighting parameter of a loss function to optimize the segmentation model; and the application reversely maps the topological defects detected by skeletonization into a weight graph and integrates the weight graph into a loss function for closed loop iteration, realizes directional repair on high-occurrence areas such as fractures and false branches, and improves the conduction efficiency of segmentation improvement to skeleton quality.

This invention discloses a computer-aided diagnostic method based on deep learning, comprising the following steps: collecting multi-source operational status data of a computer system and performing time alignment to form a system operational status data sequence; constructing a multi-scale system status sequence set; inputting the multi-scale system status sequence set into an improved TimeGPT model to generate a baseline status sequence for healthy system operation; calculating the state deviation of the system operational status data sequence and extracting the recoverability features of the deviation; performing cumulative evolution analysis across operational cycles on low-recoverability state deviations to construct anomaly evidence vectors; determining the irreversibility of risk based on the anomaly evidence vectors, generating auxiliary diagnostic results and determining the risk level; and outputting system operation early warning information based on the auxiliary diagnostic results. This invention can achieve accurate identification and risk classification of computer system operational anomalies, providing reliable support for operation and maintenance decisions and possessing significant engineering application value.

This invention discloses a method and system for pathological classification of pulmonary nodules based on dynamic phenotypic subspace inference, belonging to the field of medical image processing and computer-aided diagnosis technology. The method includes: constructing a multi-center feature template library; extracting query features and matching them with the template library, using the maximum similarity under each category as the classification criterion; constructing a joint loss function containing cross-entropy and hierarchical loss to update the feature extractor; performing gradient-free dynamic replacement of the template library based on diversity gain; and outputting prediction results by matching with a frozen template library during testing. This invention also discloses a corresponding classification system. By constructing a dynamic multi-center feature template library, this invention explicitly accommodates intra-class phenotypic diversity. Combined with ordinal consistency constraints and a dynamic template update strategy, it can effectively learn continuous feature representations of the evolution of pathological malignancy, thereby achieving dynamic matching and accurate identification of complex pulmonary nodule phenotypes and assisting in precise clinical diagnosis and treatment.

This application discloses an image processing method, a computer-aided diagnosis method for tumors, and a computing device, relating to large model technology and the field of image processing. The method includes: performing image segmentation on the image to be processed to obtain a mask image of the detection region; determining the spatial location information of the detection region in the image to be processed based on the mask image; performing denoising processing on the image to be processed based on the spatial location information to obtain an initial enhanced image; and performing detail restoration on the initial enhanced image based on a preset resolution to obtain a target enhanced image, wherein the display clarity of the detection region in the target enhanced image is higher than the display clarity of the detection region in the image to be processed. This application solves the technical problem of poor image processing performance in related technologies.

This invention relates to the field of computer-aided diagnosis, and in particular to a breast tumor identification system based on multimodal ultrasound imaging. The breast tumor identification system provided by this invention performs the following steps: acquiring a first ultrasound modality breast image, and locating a suspected first breast tumor region in the first ultrasound modality breast image; acquiring a second ultrasound modality breast image, and aligning the second ultrasound modality breast image with the first ultrasound modality breast image; based on the alignment result, locating a second suspected breast tumor region in the second ultrasound modality breast image corresponding to the suspected first breast tumor region; and identifying the confidence level of the breast tumor in the suspected second breast tumor region based on the distribution of microvessels in the suspected second breast tumor region. The breast tumor identification system based on multimodal ultrasound imaging provided by this invention, combining breast images from both the first and second ultrasound modalities, achieves more accurate breast tumor identification and localization, improving detection accuracy.

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 application discloses a brain tumor MRI image semantic segmentation method, and belongs to the technical field of medical image processing and computer-aided diagnosis. The application solves the problem of low segmentation precision based on the existing brain tumor MRI image semantic segmentation technology. The application proposes a semantic segmentation model combining the U-Net architecture with the LWD module, the MFDF module and various filters. The LWD module can keep as much information as possible in the down-sampling process. The MFDF module constructs a new directional gradient feature extraction operator and combines different direction operators by using double-channel filtering, so that the constructed multi-direction filter can extract low-frequency and high-frequency feature direction information respectively. The MFDF module transmits the detail features from the encoding module to the corresponding decoding module, thereby recovering the spatial information including the feature boundary and texture and improving the segmentation precision of the model. The application has good adaptability to the randomness of the shape, size and boundary of the brain tumor. The method can be applied to brain tumor MRI image segmentation.

This invention relates to the field of computer-aided diagnostic technology and discloses a method and system for multi-scale feature mining and intelligent risk prediction of hemorrhagic transformation (HT) in CT images. The method includes: performing standardized preprocessing on acquired raw CT images to obtain standardized CT image data; using a pre-constructed deep learning feature extraction network, sequentially performing shallow feature extraction and multi-scale deep feature mining on the standardized CT image data to obtain deep, full-dimensional features characterizing the lesion area and the overall state of the brain parenchyma; inputting the deep, full-dimensional features into a risk prediction classifier to calculate the probability value characterizing the risk of hemorrhagic transformation after ischemic stroke; and generating an attention heatmap based on the attention mechanism of the deep learning feature extraction network for visual interpretation of the prediction basis, and outputting the probability value and the attention heatmap, thereby realizing accurate and intelligent prediction and visual interpretation of HT risk in CT images.

This application relates to the field of medical neuroimaging processing and computer-aided diagnosis technology, and discloses a method based on normal white matter. 18 An Alzheimer's Disease (AD) Auxiliary Assessment System Based on F-florbetapir Retention Features. This system includes a data acquisition module for acquiring multimodal brain imaging data of subjects; an image preprocessing and segmentation module for impurity removal and target localization of the image data; a feature extraction module for extracting image features from the processed images; and a joint assessment and prediction module for AD auxiliary assessment based on the extracted features, incorporating a subject performance characteristic model and a logistic regression system. This Alzheimer's Disease (AD) auxiliary assessment system can significantly improve the accuracy of early AD diagnosis, accurately predict the rate of cognitive decline, and dynamically monitor the effect of immunotherapy.

The embodiment of the application discloses a kind of cornea multimodal data fusion method and related device, the method includes determining the coordinate and physical size of the same feature of cornea in polar structure diagram and topographic thickness chart;According to the coordinate and physical size of the same feature in polar structure diagram and topographic thickness chart, determine the similar transformation matrix between the polar structure diagram and the topographic thickness chart;According to the similar transformation matrix, polar structure data is resampled to the topographic thickness chart, obtains multimodal fusion data, or, according to the similar transformation matrix, topographic thickness data is resampled to the polar structure diagram system, obtains multimodal fusion data.The embodiment of the application greatly enhances the density of data and the relevance of information by deeply fusing the microscopic structure information and macroscopic morphological information of cornea, which is beneficial to accurately identify complex lesion patterns and improve the accuracy and robustness of computer-aided diagnosis.

A method for segmenting and 3D visualization of chest CT images, belonging to the field of medical image processing and computer-aided diagnosis technology, comprises the following steps: S1, importing and standardizing preprocessing of medical image data; S2, segmenting of multiple tissue images of the thoracic cavity based on a hybrid strategy; S3, dual-mode 3D geometric reconstruction; and S4, interactive 3D visualization and rendering. Through these steps, this invention directly achieves accurate segmentation of multiple tissues and dual-mode 3D reconstruction of surfaces and volumes without relying on high-end hardware or complex manual operations, thus improving image analysis efficiency.

This invention relates to the field of computer-aided diagnostic technology, and provides a method for constructing an intelligent pathological auxiliary diagnostic model for lipomas based on weakly supervised learning. The method includes acquiring several whole-slice images of lipomas; preprocessing the whole-slice images; constructing a structured square image patch dataset suitable for weakly supervised learning; classifying and storing the images according to their dataset and pathological label categories in a structured text index file; constructing a lightweight ViT model as the core network architecture, serializing and embedding the square image patches, learning features through a multi-layer self-attention mechanism, and connecting them to a global pooling classification head to form a weakly supervised diagnostic model that relies on image-level labels for end-to-end training; and applying weakly supervised training strategies and optimizations to the weakly supervised diagnostic model to achieve an interpretable intelligent diagnostic system for lipomas. This invention constructs an end-to-end solution suitable for weakly supervised learning of pathological images.

The application belongs to the technical field of medical image processing and computer-aided diagnosis, and discloses a method and system for predicting postoperative complications of TIPS based on vascular tortuosity, which realizes accurate quantification of the vascular tortuosity feature by pre-processing, skeleton extraction, down-sampling processing, slope chain code quantization, histogram statistics and visual interactive of the portal vein image, and establishes the correlation model between the vascular tortuosity feature and the postoperative complications of TIPS. The application quantifies the vascular tortuosity by using the slope chain code technology, and solves the defect that the traditional method cannot capture the local tortuosity feature of the blood vessel by combining with the ball drop down-sampling processing, so as to realize accurate representation of the spatial configuration complexity of the blood vessel. By establishing the correlation model between the tortuosity histogram feature and the clinical outcome, the prediction accuracy of the postoperative complications of TIPS is significantly improved, and a reliable basis is provided for early intervention. The generated interactive HTML file realizes efficient conversion from data to clinical decision, and facilitates doctors to intuitively analyze the high-risk section of the blood vessel.

The present application relates to the field of computer-aided diagnosis, and discloses a digestive tract endoscopic lesion classification model training method based on small sample learning, which unifies the annotation information of different modalities to the same coordinate system on the basis of the constructed modal time sequence diagram, forms three-dimensional spatio-temporal aligned multi-modal data, and performs classification, dynamically fuses the classified multi-modal data in a cross-modality attention manner, thereby generating a dynamic cross-modality attention weight graph, obtains cross-modality shared features and time sequence dynamic features based on the weight graph, combines the features, forms cross-modality time sequence consistency features, combines the features with the cross-modality attention weight graph, trains a meta-learning classification model, visualizes the attention weight in the form of a heat map, exports the trained meta-learning classification model and deploys it to an actual application platform, classifies new digestive tract endoscopic images, improves the training efficiency and classification accuracy, and enhances the robustness of the model.

The application discloses an early screening method for Alzheimer's disease based on voice interaction of AI accompaniment, and relates to the technical field of computer-aided diagnosis. The method comprises the following steps: S1, end-side perception and preliminary processing; S2, cloud core analysis; S3, multi-device physiological data fusion; and S4, service arrangement and feedback. The application realizes early screening and early warning with no perception and high precision.

The application discloses a stroke CT image prototype confidence calibration classification method and system, and relates to the fields of medical image intelligent analysis, computer-aided diagnosis and artificial intelligence image recognition. The method extracts global image features after preprocessing of brain CT images; a learnable category prototype is constructed and dynamically optimized; a prototype comparison constraint is established based on the cosine similarity of the global image features and the category prototype; prototype enhanced features are obtained according to the cosine similarity, and multi-scale fine processing is performed; the distance between the fine features and the category prototypes is calculated to obtain initial classification probability and initial confidence; the initial confidence is calibrated in combination with the nearest distance; a perturbation sample is constructed and an uncertainty perception consistency constraint is established; the trainable parameters of the classification network are optimized based on a total loss function to obtain a classification model, and category prediction is realized. The method can improve the category feature separability in stroke CT image classification and reduce the risk of misjudgment.

The application relates to the technical field of medical image processing and computer-aided diagnosis, and discloses a cross-modal medical image synthesis method based on task guidance and domain feature consistency. The method acquires an unpaired source domain and a target domain dataset, constructs a synthesis model containing a multi-scale generator, a double-view discriminator and a task guidance auxiliary diagnosis discriminator, generates a synthesis image and a reconstructed image through forward propagation, calculates an adversarial generation loss and a cycle consistency loss, simultaneously extracts an encoding layer feature, calculates a domain feature consistency loss by using Euclidean distance to constrain a semantic direction, fuses source domain and synthesis image features to input an auxiliary network, calculates a task guidance interaction loss and guides a generator optimization through gradient back propagation, and alternately updates model parameters based on a total objective function. The application effectively solves the problems of pathological information loss and semantic drift in cross-modal synthesis, and significantly improves the accuracy and practicality of the synthesis image in auxiliary diagnosis.

The application belongs to the field of intelligent medical computer-aided diagnosis, and relates to a method for diagnosing autism spectrum disorder based on fuzzy modeling and multi-label learning. The method comprises four parts of preprocessing, feature extraction, training stage and use stage. The rs-fMRI image of the autism spectrum disorder sample is processed into digital feature data suitable for method training and use through preprocessing and feature extraction. The training stage comprises sample synthesis, fuzzy uncertain learning, label collaborative learning, linear regression weighting and high-order functional connectivity learning. The combination of sample synthesis and linear regression weighting can effectively alleviate the imbalance between autism spectrum disorder subtypes, label collaborative learning reduces the interference of label noise on method prediction by analyzing the correlation between each autism spectrum disorder subtype, and high-order functional connectivity learning further excavates potential knowledge in the second-order functional connectivity features of autism spectrum disorder based on label prior knowledge.

This invention discloses a quantitative analysis system for airway changes in chronic obstructive pulmonary disease (COPD) based on three-dimensional reconstruction, belonging to the field of medical image processing and computer-aided diagnostic technology. The system includes an image data acquisition module, an airway tree reconstruction module, a morphological analysis module, a small airway function assessment module, a disease progression prediction module, and a result output module. It ultimately generates a comprehensive report containing three-dimensional visualized images, morphological parameters, small airway function assessment results, and disease progression prediction results. This system achieves precise reconstruction of the entire lung airway down to the 6th and 7th grade bronchi, high-precision measurement of airway morphological parameters, indirect assessment of small airway function via single inspiratory CT, and intelligent prediction of disease progression, providing comprehensive imaging support for early diagnosis, disease assessment, individualized treatment, and prognosis of COPD.

This invention belongs to the field of medical image processing technology, specifically relating to a deformable medical image registration method based on dynamic graph convolutional attention. It aims to address problems in existing technologies such as imbalance between global and local feature modeling, high computational cost, and poor adaptability to large deformations. This method acquires multi-level features from both moving and stationary medical images through a weighted dual-stream feature extraction encoder. It adaptively enhances the representation of similar anatomical structures using a dynamic feature fusion module, accurately captures global spatial dependencies and local details using a dynamic graph convolutional attention module, and iteratively optimizes the deformation field through a multi-stage deformation fusion strategy from coarse to fine, ultimately generating a precise and stable final deformation field to complete image registration. This invention effectively balances global modeling and local characterization capabilities, reduces model computation and memory usage, improves registration stability and anatomical structure alignment accuracy in large deformation scenarios, and balances registration efficiency with the physical rationality of the deformation field. It provides efficient and reliable medical image registration support for clinical scenarios such as computer-aided diagnosis and image-guided surgery.

The present application belongs to the technical field of medical image intelligent analysis and auxiliary diagnosis, and specifically discloses a thyroid nodule auxiliary diagnosis method and system based on multi-modal fusion, which is used for intelligent classification and auxiliary diagnosis of thyroid nodules. The method comprises the following steps: collecting and labeling medical image data and clinical structured data; standardizing and normalizing the data for pretreatment; constructing an image feature extraction branch and a clinical feature extraction branch to extract the feature representation of each modality; jointly modeling the image features and the clinical features through a strip perception module (SAC) to form a fused clinical-image context representation; generating channel-level adaptive parameters through a feature-level linear modulation method to dynamically adjust the image features individually; and finally completing the classification of thyroid nodules based on the fused multi-modal features. The present application realizes an image feature modeling method involving clinical structured data, which enables dynamic fusion of patient individualized clinical background for image interpretation, and provides more comprehensive, stable and reliable technical support for computer-aided diagnosis of thyroid diseases.

The present application relates to the technical field of computer-aided diagnosis, in particular to a prostate cancer multi-modal data analysis system based on cloud collaboration, which comprises a biochemical image joint acquisition module, a constraint hyperplane space construction module, a lesion texture feature extraction module, a projection correction module and a risk assessment module.In the present application, biochemical antigen concentration and gland volume parameters are converted into density reference values, a geometric subspace perpendicular to the azimuth axis is constructed in the feature space to generate a constraint normal vector, the lesion gray level dispersion is extracted and the feature deviation distance is calculated in this direction, the inner product operation is used to perform subtraction correction on the feature vectors exceeding the tolerance threshold, the texture noise interference caused by benign hyperplasia is eliminated, the image features are precisely aligned in the physiological dimension, and the specificity and accuracy of the malignant risk assessment are improved by comparing the cosine value of the calibrated feature vector with the typical cancer prototype in the cloud.

The embodiment of the application provides a task processing method, an automatic question answering method and a computer-aided diagnosis method, which comprises the following steps: obtaining an initial task processing result generated for a task processing request, wherein the initial task processing result is generated based on tool execution results of at least one tool; identifying a plurality of candidate reasoning information from the initial task processing result, wherein the plurality of candidate reasoning information comprises at least one to-be-traced reasoning information; determining a target reasoning evidence associated with the to-be-traced reasoning information from an evidence index dataset, wherein the evidence index dataset comprises a plurality of initial evidences, and the initial evidence comprises the tool execution result; and generating a target task processing result for responding to the task processing request, wherein the target task processing result comprises the plurality of candidate reasoning information and a traceability identifier set for the to-be-traced reasoning information, and the traceability identifier points to the target reasoning evidence. The application can realize point-level evidence tracing and support medical evidence-based auxiliary diagnosis.

The application provides a kind of diabetes nephropathy auxiliary identification method and system based on CT image, it is related to medical image processing and computer-aided diagnosis technical field, the method comprises: obtaining the abdominal CT image of target object;Segment kidney, perirenal fat and body composition region of interest;Extract radiomics features;Screening to obtain target radiomics features;Input radiomics model to obtain whether target object is identified result of suffering from diabetes nephropathy.The application extracts microcosmic image markers related to renal function damage from conventional CT images by comprehensively using multiple site radiomics features, realizes non-invasive, accurate auxiliary identification of diabetes nephropathy, significantly improves detection efficiency, and provides a reliable image-aided diagnosis tool for clinic.