271 results about "Lesion detection" patented technology

The invention provides a farmland disease and pest monitoring method and device and a storage medium, and relates to the technical field of agriculture, the method comprises the steps: dividing a farmland into a plurality of sub-regions, obtaining an infrared spectrum image, and segmenting the infrared spectrum image into corresponding sub-images; and calculating a vegetation stress index based on the reflectivity of the insect pest related characteristic wave band, and screening high-risk sub-regions. Risk plants are randomly extracted in a high-risk area, physiological parameters of leaves are collected, physiological health indexes of the leaves are constructed, and dynamic correction is carried out through an environment regulation coefficient according to environment data. Using the trained network model to identify the risk sample leaf scab, and calculating the scab area index. And finally, fusing the corrected leaf physiological health index and the scab area index, calculating a normalized risk value through a risk assessment function, and dividing the normalized risk value into four risk levels. Through multi-stage fusion of spectral analysis, physiological parameter correction and deep learning scab detection, accurate early warning of diseases and insect pests is realized, and the monitoring efficiency is improved.

The invention discloses a cervical cytopathy detection method based on a hypergraph convolutional network. The method comprises the following steps: performing sliding window slicing processing, unsupervised image decomposition and dyeing normalization on a cervical cytopathy image, generating normalized image input, and constructing an image input sample set; a target detection model is constructed based on YOLO11, a block-level feature extraction network (BBMM) module is embedded to enhance the perception ability, and a sparse attention module is adopted to perform key region feature enhancement; constructing a hypergraph neural network HGNN module based on a Patch-level relationship, and extracting a structural relationship between cells; integrating an uncertainty quantification mechanism, and generating a confidence thermodynamic diagram; a front-end and rear-end separated diagnosis platform is built, image uploading, detection result display, frame selection correction and interactive management are supported, and whole-process auxiliary diagnosis is achieved; the method has the advantages of high detection accuracy, high interpretability, flexible deployment and the like, and is suitable for intelligent early screening and clinical auxiliary diagnosis scenes of cervical cytopathy.

The invention relates to the technical field of medical image processing, in particular to a cross-modal image fusion detection system for endoscopic early cancer lesions, which comprises a data acquisition module for acquiring a white light endoscope and a narrow-band imaging image; the data annotation module carries out pixel-level annotation, and the data enhancement module amplifies a data set by using CycleGAN; the white light data module and the narrowband data module train feature extraction models respectively; the feature alignment and attention module solves the problem that feature scales and semantics between two modes are inconsistent, and efficient fusion is achieved. The edge enhancement module enhances feature extraction of small focuses through the generative adversarial network; the fusion model construction module fuses the features and the transition area data to generate a fusion model; and the output module processes the white light and the narrow-band imaging image and outputs a fused image. Through feature alignment, an attention mechanism and a CyclGAN data enhancement technology, the problem of insufficient medical image data is effectively solved, the model generalization ability is enhanced, and efficient and accurate early cancer focus detection is realized.

The invention provides an index construction method for a medical ultrasonic database, and relates to the technical field of ultrasonic data processing, and the method comprises the steps: reading a multi-frame image sequence from a DICOM ultrasonic database, and generating a diagnosis intention vector for each frame; analyzing the diagnosis report, and segmenting the report into a plurality of segments; lesion detection and segmentation are performed on each frame of image to obtain lesion information, and a cross-frame aggregation strategy is adopted to identify a unified lesion object; extracting a feature vector of each focus object to obtain a focus object feature vector; establishing an alignment mapping between the focus object and the report fragment by adopting triple constraints, and generating a focus report mapping table; and constructing a multi-layer index structure, and storing the focus report mapping table and the multi-layer index structure in parallel. According to the method, a multi-layer index structure comprising a metadata index, a text index, a focus object vector index and a cross-modal embedding index is formed, so that efficient organization and focus-level accurate retrieval of medical ultrasonic data are realized.

The invention relates to the technical field of image focus detection, in particular to a fiber endoscope image focus detection method and system, and the method comprises the following steps: providing a data quality guide interface; capturing narrow-band light images of the endoscope away from a first preset position and a second preset position of the intestinal wall in the axial movement process, calculating brightness gain values of a blue light channel and a green light channel, calculating an asymmetric scattering correction coefficient, and updating indication of color information calibration integrity; tracking the pixel moving speed of the interferent in the view in the propulsion operation process, calculating the relative depth of the interferent, and updating the indication of the validity of the depth data of the interference layer; identifying the image area which is not shielded by the interferent, and updating the indication of the information coverage degree of the background area; triggering an image synthesis operation; performing color compensation on the image information of the image area which is stored in the background canvas and is not shielded by the interferent; reconstructing a clear image; and performing focus detection on the clear image. The method improves the accuracy of focus detection.

The invention belongs to the technical field of medical image analysis, and relates to a lesion detection method and system based on multi-scan interactive deformable Mama, and the method comprises the steps: 1, image block embedding; 2, multi-scale feature extraction and interaction in the backbone network are scanned in parallel; 3, feature pyramid optimization based on dynamic weighted scanning fusion; 4, performing multi-scale fusion; according to the invention, through the adaptive scanning network and the deformable scanning mechanism, the characterization problem of the morphological heterogeneity of the oral cancer focus and the pulmonary nodule microstructure feature is effectively solved, the double breakthrough of the detection precision and the calculation efficiency is realized, and an efficient and reliable solution is provided for multi-cancer medical image analysis.

The invention discloses a vascular access lesion recognition method and system based on target detection, and relates to the technical field of medical image processing, and the method comprises the steps: carrying out the cardiac cycle phase division according to an electrocardiogram signal, calculating a displacement vector field between adjacent frames of a blood vessel DSA image sequence, constructing a motion compensation model, and generating a stable DSA sequence; segmenting the stable DSA sequence into binary vascular mask images through a U-Net segmentation model, tracking motion displacement of contrast agent particles in continuous frames by using a particle image velocimetry algorithm, generating a blood flow velocity vector field, and calculating an eddy current intensity feature map; and carrying out channel cascading on the binarized blood vessel mask image and the vortex intensity feature map to generate a blood vessel feature tensor, and generating a lesion detection result by improving a YOLOv7 model. According to the method, the accuracy, robustness and clinical applicability of vascular disease recognition are improved, and a technical closed loop from multi-modal data processing to automatic diagnosis report generation is realized.

The invention discloses a diabetic foot early-stage detection method combining infrared and visible light imaging, and relates to the technical field of diabetic foot medical imaging diagnos.The diabetic foot early-stage detection method comprises the steps that multi-mode image collection and standardization processing are conducted, infrared images and visible light images are synchronously collected, and standardization processing such as size normalization is conducted; image registration and space alignment are carried out, marking points are set based on foot anatomical features, and feature extraction, mismatching point elimination and transformation matrix calculation are carried out; extracting and screening multi-dimensional features, extracting temperature and structural features, and screening by using a Relief-F algorithm; feature lesion recognition and classification are fused, and lesion probability is output through a double-branch convolutional neural network; carrying out detection result verification and feedback optimization, and comparing a clinical diagnosis optimization model; and generating a detection report and storing data, and generating a report containing the fused image. The early lesion detection precision is improved through multi-modal fusion, individual and environment differences are adjusted and adapted in a personalized mode, and reliable technical support is provided for clinic.

The invention relates to the technical field of disease diagnosis, in particular to a sacroiliac joint lesion intelligent identification method and system based on MRI, and the method comprises the steps: data preparation and enhancement, multi-expert collaborative labeling, mixed 3D-2D model processing, verification and optimization, and deployment and interaction. Compared with the prior art that a scheme for detecting the sacroiliac joint lesion by adopting a single 3D CNN or 2D CNN model has the problems of inaccurate positioning of an anatomical structure and loss of inter-layer feature association, resulting in insufficient sensitivity and specificity, the method provided by the invention has the advantages that through an improved hybrid 3D-2D model architecture, spatial features are extracted by utilizing the 3D CNN and an inter-layer dependency relationship is modeled in combination with Transform, so that the sensitivity and the specificity of the sacroiliac joint lesion detection are improved, and the detection accuracy of the sacroiliac joint lesion detection is improved. Meanwhile, spatial pyramid pooling and a channel attention module are adopted to enhance the multi-scale feature extraction capability, so that the method has the advantages that the lesion detection sensitivity and specificity are remarkably improved, the bone marrow edema region can be more accurately recognized, and the misdiagnosis rate is reduced.

The invention discloses a cerebral apoplexy focus detection method and system, and belongs to the technical field of medical image detection. Extracting a fusion feature map of the brain image; for each region type, obtaining a representative feature which has the highest similarity with the feature at each pixel point position in the fused feature map in the class prototype set and carries a corresponding region type label, and further determining the region type to which each pixel point position in the fused feature map belongs so as to obtain a corresponding pseudo-label map; the class prototype set comprises representative features of different region types and is obtained in the training process of the system, and feature distribution of different region types in the memory bank is calculated through a Gaussian mixture model; for each region type, sampling is carried out based on feature distribution of the region type, and a plurality of representative features are obtained; the prototype-like set in the cerebral apoplexy detection method has real global context perception ability, can clearly distinguish the focus and various complex background structures, and can accurately realize cerebral apoplexy detection.

The invention discloses a tiny residual focus detection method and system based on ultra-high depth sequencing, and relates to the technical field of tiny residual focus intelligent detection.The tiny residual focus detection method comprises the following steps that on the basis of a sequencing library, splitting is conducted according to a sample index to obtain a to-be-detected sample, and a consensus sequence is obtained according to a molecular identifier of the to-be-detected sample; based on a consensus sequence, filtering out the consensus sequence of which the mass value is less than 25 or the family size is less than 3, and combining a variation type and a distance from a fragment edge as noise introduced into an original nucleic acid molecular chain; a context sequence (context) and a chain direction are used as noise for introducing the capture level of PCR amplification; on the basis of the noise level, the circulating tumor DNA level is estimated in combination with tumor priori knowledge, and the MRD state is determined by detecting the significance of molecular signal sources. According to the invention, the sensitivity and specificity of MRD detection are improved.

The embodiment of the invention provides a cerebral apoplexy focus detection and scoring method and device based on a multi-modal medical image. The method comprises the following steps: acquiring medical images of various different modals of a suspected acute ischemic cerebral apoplexy patient; performing registration fusion and focus labeling on the medical images of different modalities based on an attention mechanism to obtain a labeled first modal image; training a target detection model of a YOLOv8 framework based on Swin-Transform improvement by using the labeled first modal image, and carrying out target detection on the to-be-detected image based on the trained target detection model to obtain an infarction region detection result; training a semantic segmentation model by using the labeled ASPECT scoring and partitioning brain atlas, performing scoring region segmentation on the to-be-detected image based on the trained semantic segmentation model, and outputting the ASPECT scoring and partitioning brain atlas; and mapping the infarct area detection result to the ASPECT score partition brain map, and calculating to obtain an ASPECT score.

The invention discloses an intelligent bronchial endoscope focus detection method, computer equipment and a storage medium. The intelligent bronchial endoscope focus detection method comprises the steps that real, reliable and diversified bronchial endoscope examination images are collected; through data preprocessing, labeling and data division, a bronchial focus detection data set is constructed; an efficient bronchial focus detection network is constructed, and improvement is carried out through multiple attention mechanisms and a convolution module; designing a loss function and training the network to obtain an optimized bronchial focus detection model; and performing focus detection on the acquired image in the real-time bronchoscopy video, and displaying a result. Based on the deep learning technology, the deep neural network model is trained to carry out precise focus type detection on the bronchial endoscope image, real-time bronchial lesion prompt information is provided for endoscope operators, the lesion omission problem during bronchial lesion examination is effectively relieved, the bronchoscopy process is standardized, the endoscope examination quality is improved, and the bronchial lesion detection efficiency is improved. And the workload of operators is reduced.

The invention relates to the technical field of medical image intelligent diagnosis, and provides an interpretable lung CT image intelligent diagnosis method and device, and the device comprises an image calling module, an image processing module, an image analysis module and a result display module. According to the method, identity information of a patient is read to automatically verify and authorize, and an electronic CT image is called and stored in a data storage card through an encryption transmission channel. And the image processing module performs denoising, enhancement and interpretability analysis on the original image to generate a thermodynamic diagram to assist in decision making. The image analysis module completes lesion detection and classification, verifies the consistency between a model decision and doctor experience through a thermodynamic diagram, and optimizes network parameters in combination with feedback data. And the result display module displays a diagnosis result and a thermodynamic diagram in real time, and supports multi-terminal cooperation and data archiving. The device supports data sharing and remote consultation, the efficiency and convenience of diagnosis are improved, and the wide application prospect of artificial intelligence in the field of medical diagnosis is shown.

The invention discloses a medical image artifact identification and elimination method based on a big data technology, and relates to the technical field of medical image processing, and the method comprises the steps: carrying out the preprocessing of collected image data based on gray normalization, and then carrying out the semantic segmentation and ROI positioning of the image content; and performing lesion segmentation on the positioned image content, selecting lesion features for quantification and fusion, performing model verification, and performing distributed deployment on the verified lesion segmentation model. According to the method, the problems of high missed detection rate of small nodules and high missed diagnosis risk of malignant lesions are solved through the lesion detection model, the false positive rate is reduced, the recall rate of the malignant lesions is improved, and through the lesion segmentation model, the segmentation adaptability to lesions of different sizes is improved, clear segmentation boundaries are obtained, surgical planning is assisted, and boundary positioning errors are reduced.

The invention discloses a focus intelligent detection and diagnosis system based on multi-modal medical image fusion, and relates to the technical field of medical image processing. A molybdenum target image, an ultrasonic image and a magnetic resonance image of the mammary gland of the patient are acquired through the data acquisition module; a data registration module is used for carrying out partition affine and local refinement registration on the multi-modal image by taking the molybdenum target image as a geometric anchor point and combining parameters such as compression force; extracting registered fusion feature data through a data fusion module; generating a candidate focus set by a focus detection module; finally, the risk assessment module calculates a comprehensive risk score through weighting, correction and consistency verification processes based on a plurality of interpretable feature indexes. And the output module generates a visual diagnosis result. According to the invention, intelligent detection and risk assessment of rechecking of breast lesions are realized, and the diagnosis accuracy and clinical reliability are effectively improved.

The invention relates to the field of medical image processing, in particular to an oral medical image precision optimization method based on multi-modal data. Comprising the steps of obtaining oral cavity CBCT, X-ray and MRI images, performing preprocessing and spatial registration, respectively extracting a three-dimensional skeleton structure, two-dimensional texture density and soft tissue features, realizing multi-modal feature weighted fusion through an adaptive fusion module based on an attention mechanism, and completing oral cavity structure segmentation and lesion detection by using a convolutional neural network. According to the method, multi-source heterogeneous image information can be effectively integrated, and the lesion recognition accuracy and segmentation precision are remarkably improved.

The present disclosure relates to a dental lesion detection method and a system to which the method is applied. A dental lesion information visualization method according to the present disclosure includes the steps of acquiring data of a lesion analysis model which outputs data on the type and location of a lesion included in a panoramic image obtained by capturing an image of the oral cavity of a patient, and inputting a panoramic image into the lesion analysis model to output data on the type and location of a lesion and a lesion detection confidence score.

The invention relates to the technical field of medical images, in particular to a medical image intelligent detection and auxiliary diagnosis system based on deep learning, and the system comprises a data access module which is used for obtaining medical image data and clinical text data of a patient; the data fusion module is used for generating a focus feature vector and a text feature vector, and performing cross-modal alignment and fusion to generate a fusion feature vector; the diagnosis analysis module is used for executing focus detection, focus segmentation and focus classification tasks, generating a diagnosis result and generating a diagnosis label based on the diagnosis result; the decision generation module is used for mapping the generated execution result to a preset medical knowledge base and performing deep reasoning to generate an auxiliary diagnosis decision; the decision auditing module is used for performing confidence scoring on the auxiliary diagnosis decisions and selecting the auxiliary diagnosis decision with the highest confidence score as the final auxiliary decision; and the data visualization module is used for carrying out visualization processing on the auxiliary decision and the diagnosis result.

The invention relates to the technical field of image processing, and discloses an improved StarNet-YOLOv13-based unmanned aerial vehicle field tobacco virus disease lightweight detection method, which comprises the following steps: acquiring a to-be-detected image of a field tobacco plant, and then inputting the to-be-detected image into a trained tobacco virus detection model to obtain a detection result of the tobacco plant; wherein the tobacco virus detection model is obtained by replacing a backbone network with a star network, replacing a C3K2 module in a neck network with a feature fusion module and replacing a detection head with a DetectMBConv detection head in a YOLOv13 model; the feature fusion module is constructed by introducing a partial convolution mechanism into the C3K2 module; thus, through the star network (StarNet), the feature fusion module (DSC3k2PConv module) and the DetectMBConv detection head, the small target scab detection capability and the complex scene robustness can be improved while the parameter and calculation overhead can be reduced, so that the tobacco virus detection model can meet the deployment requirement of the computing power limited equipment side, such as an unmanned aerial vehicle, and the detection precision is ensured at the same time.

An ultrasonic diagnostic apparatus includes: a lesion detection unit (26) that detects a suspected lesion region in a mammary gland region of a subject based on an ultrasonic image in which the mammary gland region is imaged; a mask data creation unit (27) that creates mask data of the detected suspected lesion region; an exclusion region setting unit (28) that sets an exclusion region to be excluded from a target of a glandular tissue component evaluation based on the mask data; and an evaluation unit (29) that performs the glandular tissue component evaluation on an evaluation target region obtained by excluding the exclusion region from the mammary gland region.

The invention relates to the technical field of medical images, in particular to a multi-modal medical image registration and fusion analysis method, which comprises the following steps of: eliminating image noise and artifacts based on a modal adaptive filtering strategy; constructing a pyramid type feature extraction network to realize multi-scale feature extraction, calculating feature matching degrees among different modal images, and dynamically adjusting matching weights by combining feature differences among modals; a focus area attention mask is constructed, targeted enhancement of registration image features is realized, and a hierarchical fusion strategy is adopted to evaluate the quality of a fused image; and constructing a multi-task deep learning model to complete focus automatic detection, segmentation and benign and malignant preliminary judgment on the fused image. According to the multi-modal medical image registration and fusion analysis method, a three-layer feature pyramid is constructed, a multi-feature fusion matching cost function is introduced, and cross-modal feature matching is optimized through an adaptive weight iteration nearest point ICP algorithm, so that the information richness, marginal definition and focus discrimination of a fused image reach the standard.

The invention discloses an intelligent detection method for a brain tumor focus area, and relates to the technical field of medical image processing. The method comprises the following steps: acquiring a multi-modal image; the multi-modal image is an MRI (Magnetic Resonance Imaging) image generated according to T1 weighting, T2 weighting and an FLAIR sequence; the multi-modal image is preprocessed, and a normalized image is obtained; constructing a focus detection model; the focus detection model adopts a double-branch network structure and comprises a global branch, a local branch and a weighted fusion module; the global branch and the local branch are both connected with the weighted fusion module; the weight fusion module adopts a dynamic weight fusion strategy; inputting the normalized image into the focus detection model to generate a preliminary focus segmentation result; and performing post-processing optimization on the preliminary focus segmentation result to generate a final focus positioning result. According to the invention, the detection precision of the brain tumor lesion area can be improved.

The invention discloses an endoscope report generation method, device and equipment and a readable storage medium, and is applied to the technical field of computer vision and deep learning, and the method comprises the steps: obtaining an endoscope real-time video stream, and determining a target inspection type based on the time sequence characteristics, spatial characteristics and motion characteristics of the endoscope real-time video stream; determining a global feature and a local feature of the endoscope real-time video stream, splicing the global feature and the local feature, and determining a target inspection part based on a spliced feature obtained by splicing; performing real-time lesion detection on the endoscope real-time video stream to obtain a lesion area; and generating an examination report based on the target examination type, the target examination part and the lesion area to obtain a target endoscope report. As the doctor does not need to manually determine each index generation report, the endoscope report generation efficiency can be improved, and the target examination part can be determined based on the global features and the local features, so that a plurality of examination parts can be accurately determined.

This application relates to the field of medical technology and provides a medical application scenario matching method, electronic device, and computer program product. The medical application scenario matching method includes: acquiring a medical image sequence; determining image information of the medical images in the medical image sequence, the image information including key information, which includes one or more of the following: imaging object information, phase information, lesion detection information, and image quality information of the corresponding medical image; and outputting at least one target application scenario adapted to the medical image sequence based on the key information. Embodiments of this application can prevent doctors from using unsuitable medical image sequences in specific application scenarios, thus helping to improve doctors' work efficiency.

An ultrasound diagnostic apparatus includes: an image acquisition unit (36) that performs a scan using an ultrasound probe (1) to acquire ultrasound images of a breast; a mammary gland region extraction unit (25) that extracts a mammary gland region from the ultrasound images; a thickness calculation unit (26) that calculates a thickness of the mammary gland region in a depth direction; a lesion detection unit (27) that detects a suspected lesion region for the ultrasound images; a frame selection unit (29) that selects, as an evaluation target frame group, at least frames which exclude a frame in which the suspected lesion region is detected, and in which the thickness of the mammary gland region is equal to or greater than a thickness threshold value, among a plurality of frames; and an evaluation unit (32) that performs a glandular tissue component evaluation on the ultrasound image of the evaluation target frame group.

Mechanisms are provided for detecting lesions in diffusion weighted imaging (DWI) images. The mechanisms receive a first set of DWI images corresponding to a anatomical structure, from medical imaging computer system(s). The first set of DWI images comprises a plurality of DWI images having at least two different b-values. The mechanisms generate a second set of DWI images from the first set of DWI images based on at least one predetermined criterion. The second set of DWI images comprises different DWI images having different b-values. The mechanisms extract feature data from the second set of DWI images, input the feature data into at least one computer neural network, and generate an output from the neural network(s) comprising at least one of a lesion classification or a lesion mask based on results of processing, by the neural network(s), of the feature data extracted from the second set of DWI images.

The invention relates to the technical field of medical image processing, and provides a gastric cancer simulation acetic acid dyeing method and system based on a generative adversarial network. The method comprises the steps of image acquisition, image preprocessing, lesion detection, lesion judgment, simulated dyeing output and the like. A single-stage instance segmentation model is adopted to identify a suspected lesion area, and a generative adversarial network is introduced to realize acetic acid staining simulation of a white light image. The system comprises an image acquisition module, a preprocessing module, a lesion detection module, a judgment module, a dyeing simulation module and a display module. According to the method, the image with the dyeing characteristic can be generated without actually spraying acetic acid, the image is used for assisting in judging the lesion area of the gastric mucosa, and the efficiency and consistency of auxiliary diagnosis are improved.

The invention discloses a retinal vessel segmentation and lesion detection method based on incremental learning. The method comprises the specific steps that firstly, an original image of a data set STARE is acquired, and preprocessing such as segmentation and data enhancement is carried out on an original retina image; then, a VGAT-Net-IL network model is constructed, the network takes a coding-decoding symmetric structure as a trunk, a visual cortex mechanism is simulated through an adaptive receptive field module to dynamically adjust a receptive field, and local details and global features of the retinal vessels are cooperatively extracted; meanwhile, a dynamic bimodal attention module is innovatively integrated, variable convolution is introduced into the dynamic bimodal attention module to adaptively adjust a sampling position, a blood vessel region is precisely focused in combination with a space and channel attention mechanism, and after the dynamic bimodal attention module, a Bayesian semantic association module is introduced to generate features containing semantic association; in order to solve the problem that old knowledge is easy to forget when a model learns new lesion features, an incremental learning technology training model is introduced. According to the method, the retinal vessel segmentation precision and the lesion detection capability are improved, and a reliable image analysis basis is provided for retinal disease diagnosis.

The invention discloses a pulmonary tuberculosis focus map segmentation system based on symmetric similarity and dynamic sample amplification, which comprises a sternum suppression network module, an entropy-driven sample number dynamic amplification module, a pulmonary tuberculosis focus detection module and a sternum suppression network module, and is used for removing a sternum image in a chest X-ray map; the entropy-driven sample dynamic amplification module is used for carrying out dynamic amplification on the number of sample images based on the complexity of the image and the existing training state of the model for a single image; specifically, for each image, an information entropy is calculated for probability distribution output by a model of each training round; in the early stage of training, the number of training image samples is amplified slightly, and the number of amplified samples is increased along with model training; and the pulmonary tuberculosis focus detection module is used for designing a pulmonary tuberculosis focus detection network model by using the target detector and the symmetric similarity of the pulmonary tuberculosis images, and segmenting a tuberculosis focus map from the X-ray map.