26 results about "Pulmonary parenchyma" patented technology

A lung CT blood vessel image segmentation and reconstruction system based on multiple interpretable features performs further fine-grained segmentation on the basis of main airway features through a feature extraction module to obtain a plurality of connected domains, performs multi-stage feature extraction on the connected domains, and outputs multi-scale feature information; the blood vessel segmentation module generates an information matrix according to the indexes and the pulmonary parenchyma mask, generates a blood vessel network segmentation result through an adversarial network and performs post-processing; and the model reconstruction module performs three-dimensional reconstruction on the blood vessel network segmentation result and the pulmonary parenchyma mask to obtain a 3D model. According to the method, on the basis of anatomical priori knowledge of pulmonary vessels and airways, a large amount of multi-scale feature information is utilized, the information loss of the two-stage segmentation network is reduced, and the network adaptability and the learning ability of the relation between pixels under the complex condition are improved. In the aspect of system design, a modular design and management mode is adopted, efficient resource access is achieved, and meanwhile the operability and usability of the system are improved through end-to-end process design.

The invention relates to the technical field of medical informatics, and provides an interstitial lung disease HRCT image analysis method and system based on artificial intelligence. The method comprises the following steps: performing pulmonary parenchyma segmentation processing on an input HRCT image to obtain a pulmonary parenchyma region; performing multi-category lesion segmentation on the pulmonary parenchyma region to obtain a segmentation mask; performing quantitative calculation on lesion distribution characteristics according to the segmentation mask to obtain lesion distribution parameters; and carrying out image mode classification according to the segmentation mask and the lesion distribution parameters to obtain a classification result. According to the method, the efficiency and precision of HRCT image analysis are improved, and the application range of HRCT image analysis is expanded.

The application discloses a kind of X-ray film lung disease screening systems of fusing multi-level features, including lung parenchyma segmentation module, lung disease preliminary screening module, multi-level feature construction module, lung disease screening module;Lung parenchyma segmentation module is used to obtain lung parenchyma part from complete chest X-ray film segmentation;Lung disease preliminary screening module is used to construct based on feature consistency variation auto-encoding generation adversarial network and train it, and obtains preliminary screening abnormal score using trained generation adversarial network;Multi-level feature construction module is used to extract features of different semantic levels, including the extraction of bottom visual features, middle layer depth features and high layer experience features;Lung disease screening module is used to construct lung disease screening model using multi-level features and the abnormal score obtained by lung disease preliminary screening module, and obtains the final lung disease classification result.The present application can effectively solve the problem that current computer-aided lung disease screening field research is difficult to be applied to practical clinical scene.

This application relates to a method, apparatus, device, medium, and program product for quantifying CT features of idiopathic pulmonary fibrosis. The method includes: acquiring a medical image of the lung to be processed; segmenting the lung parenchyma in the medical image to obtain bilateral lung regions and total lung volume; segmenting the bilateral lung regions to obtain multiple imaging features related to idiopathic pulmonary fibrosis, and determining the volume percentage corresponding to each of the multiple imaging features related to idiopathic pulmonary fibrosis and the total lung volume; and determining the predicted functional impairment value corresponding to the volume percentage of the multiple imaging features related to idiopathic pulmonary fibrosis based on a pre-generated linear regression model, wherein the linear regression model represents the correlation between the volume percentage of the multiple imaging features related to idiopathic pulmonary fibrosis and various lung function indicators. This method can improve processing efficiency.

The application belongs to the technical field of image recognition, and discloses a weakly supervised interstitial lung disease lesion recognition method based on multiple example learning, which comprises the following steps: step 1: acquiring CT image samples; step 2: selecting part of the CT images, and manually labeling the lung parenchyma in the images; step 3: establishing a lung parenchyma segmentation model through a saliency segmentation algorithm, inputting the manually labeled CT image samples to perform training and testing, and obtaining a trained lung parenchyma segmentation model; step 4: training a lesion recognition model using a multiple example learning algorithm; step 5: acquiring a to-be-recognized CT image sample, inputting the lung parenchyma segmentation model to perform segmentation, and then inputting the segmented data sample into the lesion recognition model to obtain a lesion position. The application can realize the visual labeling of interstitial lung disease through a small amount of labeling, and greatly improves the recognition efficiency.

A tool to create virtual lesions inside a 3D lung tumor image. The image can be an MRI or CT image of a patient's lung to be treated. This virtual pre procedural ablation allows the operator to identify optimal ablation sites and select the optimal ablation parameters for the given anatomy. Also, the actual procedure will be performed with the lung parenchyma surrounding the tumor preventing ultrasound to penetrate beyond the tumor walls. A diagnostic mode will guide the operator to optimize ablation parameters. This virtual pre ablation, the parenchymal ultrasound barrier and the diagnostic catheter operation should enable the operator to conduct the therapeutic procedure safe, fast and effective.

The application relates to a lung nodule detection method, device and equipment based on an improved network and a storage medium. The method comprises the following steps: processing each CT original image in an acquired image sample set to extract a corresponding lung parenchyma image, so as to reduce the amount of data to be processed and facilitate observation of the effectiveness of detection, and a lung nodule detection neural network used in the method is obtained by improving a YOLOv5 network, wherein in a backbone unit, a MetaAconC activation function is used to replace original activation functions in part of a convolution structure, a CoordAtt attention mechanism structure is added before an SPPF structure, and a BiFPN structure is used in a neck unit to perform multi-size feature fusion, so that the improved YOLOv5 network is more suitable for detection of lung nodules in medical images, and the detection is more accurate and efficient.

The present disclosure provides a CT image processing method, device, equipment, storage medium and program product, relating to deep learning technology, AI medical technology, comprising: determining a lung parenchyma region in a computed tomography (CT) image, and cutting out an initial lung parenchyma image from the CT image according to the lung parenchyma region; processing the initial lung parenchyma image to obtain a lesion segmentation mask; processing the initial lung parenchyma image to obtain a predicted lesion region in the initial lung parenchyma image; determining a target lesion region and a target lesion mask corresponding to the target lesion region according to the lesion segmentation mask and the predicted lesion region, wherein the target lesion mask is located in the target lesion region. In this implementation, the lesion region is identified by segmentation and detection, and the target lesion region and the target lesion mask inside the target lesion region are obtained by fusing the two identification results, thereby reducing the probability of missed detection.

The invention discloses a pulmonary nodule joint registration segmentation system fusing anatomical consistency and semantic priori, and the system comprises an anatomical consistency constrained registration segmentation joint learning module which is used for obtaining a reference CT image, a floating CT image and a pulmonary parenchyma mask corresponding to the reference CT image and the floating CT image in a pulmonary nodule follow-up visit, inputting the reference CT image and the floating CT image into a registration network, aligning the floating CT image to the three-dimensional dense deformation field of the reference CT image; and the semantic priori guided pulmonary nodule fine segmentation module is used for transforming the pulmonary nodule mask of the floating CT image into a coordinate system of the reference CT image based on the three-dimensional dense deformation field to obtain nodule semantic priori, and inputting the reference CT image, the nodule semantic priori and the three-dimensional dense deformation field into a pulmonary nodule fine segmentation network to realize pulmonary nodule fine segmentation of the reference CT image. According to the method, deep coordination of registration and segmentation is realized, so that more stable registration and more accurate pulmonary nodule segmentation are obtained on multi-temporal CT.

The application provides a lung nodule detection method based on deep learning, which comprises the following steps: A, performing parenchymal segmentation on a three-dimensional lung CT image; B, sequentially processing the lung parenchymal image after being divided into blocks to obtain a sparse matrix; C, extracting three-view information of the sparse matrix for false positive screening; D, building a network model; and E, using the trained network model to detect lung nodules and output the detection results. The three-view false positive auxiliary module is combined, directly embedded into an end-to-end framework, and the three-view self-attention information of the sparse three-dimensional image is used to help screen out false positive regions. On the one hand, the problem of learning attention in a complex 3D scene is solved. On the other hand, the detection and false positive region screening are designed into an end-to-end training model, the detection speed and detection accuracy are improved, the overall complexity of the model is reduced, the model training convergence speed is improved when the model is trained, and the loss function is trained uniformly.

A system for detecting an air leak in the lung parenchyma and / or airway may have a heater configured to vaporize at least one fluid into an aerosol. A conduit system may include a conduit portion configured to be received in a user's airway. A motive flow source is connected to the conduit system for inducing a flow of the aerosol into the conduit portion. A controller is configured for operating the heater to generate the aerosol, and for controlling the motive flow source to induce the flow of the aerosol into the conduit portion at a flow rate of a given level. A method for detecting an air leak in the lung parenchyma and / or airway is also provided.

This invention discloses a method and related equipment for constructing an ultrasound diagnostic training model for lung diseases. The method includes: acquiring magnetic resonance imaging (MRI) data of the chest of a target subject; performing three-dimensional reconstruction and structural segmentation on the MRI data to generate a three-dimensional anatomical digital model of the lung, including the lung parenchyma, pleura, diaphragm, ribs, and mediastinal structures; optimizing the structure, layering the model, and annotating material properties using three-dimensional modeling software to generate a three-dimensional printing model file; constructing a physical lung training model based on the three-dimensional printing model file using a multi-material three-dimensional printing device, and setting pathological simulation structures in a preset area of ​​the model to simulate the ultrasound imaging characteristics of diseases such as pulmonary consolidation, pleural effusion, pneumothorax, and pulmonary edema. The training model constructed by this invention has a realistic anatomical structure, is reusable, and can present typical lung ultrasound imaging characteristics under real ultrasound equipment.

The invention provides a lung image recognition method and system for clinical diagnosis of the respiratory medicine department. The method comprises the steps that a binary mask containing complete lung parenchyma is obtained from a lung image; segmenting a target lung field image from the lung image based on the binary mask, and extracting a texture saliency map from the target lung field image; performing pixel-level fusion on the texture saliency map and the target lung field image to obtain a lung feature image, and performing multi-resolution pyramid decomposition on the lung feature image to obtain a Gaussian pyramid layer and a Laplacian pyramid layer; direction gradient histogram features and local binary pattern features are extracted from the Gaussian pyramid layer and the Laplacian pyramid layer respectively, and then a multi-resolution joint feature vector is constructed; and inputting the multi-resolution joint feature vector into a pre-trained image analysis network, and positioning a focus area in the lung image. According to the technical scheme provided by the invention, the lesion area in the lung image can be identified under the coupling interference of the anatomical structure and the pathological features.

The application provides a lung recognition processing method and device and a server, relates to model processing technology, and the method comprises the following steps: obtaining a model recognition instruction, the model recognition instruction comprises a lung model identifier, determining a lung model corresponding to the lung model identifier, and the lung model comprises a lung parenchyma model, a trachea model, a pulmonary vein model and a pulmonary artery model. Based on the growth information of at least one of the trachea model, the pulmonary vein model and the pulmonary artery model, a plurality of initial segmentation cross sections of the lung parenchyma model are determined. According to at least one of the intrasegment trachea, intrasegment vein and intrasegment artery in each initial lung segment, a plurality of target segmentation cross sections of the lung parenchyma model are generated. According to the target segmentation cross sections of the reconstructed lung model, the distribution information of each lung segment can be obtained, thereby helping to improve the accuracy of the surgical plan, reduce the surgical risk index, improve the surgical success rate, and solve the technical problem that it is difficult to recognize the distribution of the intrapulmonary trachea, blood vessels and lung segments.

This invention relates to an animal model of mediastinal lymph node metastasis in lung cancer and its construction method. The core of this invention lies in the precise intrapulmonary in situ microinjection technique to directly implant human lung cancer cells into the lung parenchyma of immunodeficient mice. Utilizing the natural lymphatic drainage pathway of the lung tissue, tumor cells are induced to migrate to the mediastinal lymph nodes, thus successfully constructing a complete metastasis chain model from the primary tumor to regional lymph nodes. This model can more realistically simulate the microenvironment and process of lung cancer lymph node metastasis, and is suitable for metastasis mechanism research, drug evaluation, and the development of personalized treatment strategies, possessing high translational medicine value.

The application discloses an activity / inactivity tuberculosis recognition system based on an improved 3D network, which comprises an image feature acquisition module, a data preprocessing module, an image segmentation module and an image classification recognition module. The image feature acquisition module is used for acquiring lung tuberculosis CT chest image features. The data preprocessing module is used for performing data preprocessing on the acquired lung tuberculosis CT chest image features. The image segmentation module is used for segmenting the preprocessed lung tuberculosis CT chest image features to acquire lung parenchyma image features, and a segmentation model adopted is a 3D ResUNet segmentation model. The image classification recognition module is used for performing prediction classification on the lung parenchyma image features after image segmentation. An image classification model adopted is a 3D ResUNet50 classification model, and the 3D ResUNet50 classification model is combined with a multi-scale attention module to obtain image output features. Then, grouping convolution and channel shuffling are used to process the image output features, the categories of active and inactive tuberculosis are predicted, and the confidence score of the model is generated. The application can improve the CT image classification accuracy of the model.

The present invention relates to nucleic acid cassettes for gene therapy, in particular to a promoter and promoter / enhancer combination for improving transgene expression in a pulmonary parenchyma-specific / preferential manner. The invention also relates to nucleic acid cassettes comprising said promoters and promoter / enhancer combinations, viral and non-viral vectors comprising such nucleic acid cassettes, and the use of such nucleic acid cassettes and vectors for increasing the expression of therapeutic proteins by pulmonary parenchymal cells.

The invention discloses a fusion auxiliary decision model construction method and system for pneumonia image interpretation, relates to the technical field of intelligent auxiliary diagnosis, and proposes the following scheme: obtaining a pneumonia sample image and a healthy lung image, constructing an interpreter and a locator, extracting lung parenchyma local texture from the healthy lung image, and carrying out clustering discretization to obtain a fusion auxiliary decision model; a discrete vector set representing health textures is obtained to serve as a health codebook, and a lesion area in the pneumonia sample image is recognized through a locator. According to the method, the health codebook is constructed, the anti-fact health image is generated, and the current interpretation value is fed back to the positioner parameter update through the inner layer iteration triggered by the preset health threshold value, so that the defect that the interpretation conclusion loosely corresponds to the focus hot area and is easily interfered by the background clues irrelevant to the focus to cause insufficient credibility in the existing scheme is overcome; the interpretation conclusion can be verified by anti-fact contrast, and interpretable output that the positioning evidence is consistent with the interpretation basis is realized.

The present application relates to the technical field of medical image analysis, and provides a lung image registration method and system based on a cross-scale reverse refinement mechanism, which comprises the following steps: acquiring a moving image and a fixed image of a lung, obtaining a multi-scale moving feature map and a multi-scale fixed feature map through an encoder respectively, and obtaining a multi-scale deformation field through a deformation field estimator; uniformly up-sampling the low-scale deformation field to the same resolution as the highest-scale deformation field, taking the highest-scale deformation field as a guide signal, guiding and correcting each up-sampled deformation field by using a cross-scale deformation refinement network based on KAN, and obtaining a high-resolution guided and corrected multi-scale deformation field; generating a final deformation field by using an adaptive weight fusion network, processing the moving image, obtaining a deformed moving image, and aligning the deformed moving image with the fixed image in the spatial structure. The present application ensures the accurate alignment of local anatomical structures such as lung parenchyma capillary vessels and bronchial tree.

The invention discloses a CT image classification method fusing CT segmentation and multi-dimensional representation. The method comprises the steps that a chest CT image is acquired and preprocessed; and performing lung parenchyma region extraction on the chest CT image by using the pre-trained lung parenchyma segmentation network to obtain a lung region slice. Inputting the lung region slices into a two-dimensional convolutional neural network for local feature extraction, and generating two-dimensional texture feature representation; and inputting a three-dimensional convolutional neural network to carry out voxel-level feature extraction, and generating a three-dimensional spatio-temporal context feature representation. And fusing the two-dimensional local texture features and the three-dimensional spatio-temporal context features by using a cross-dimension feature fusion module through a cross attention mechanism to generate fused features. And inputting the fusion feature into a classifier, and outputting a classification result of the chest CT image. According to the invention, through combination of cross-dimensional fusion of two-dimensional and three-dimensional features, the feature expression capability is improved, and the accuracy of image classification is optimized.

The application discloses a lung artery and vein extraction method based on a CT image and belongs to the technical field of medical image processing. The method comprises the following steps: performing anisotropic diffusion filtering on a three-dimensional CT image to obtain a smooth image; segmenting a lung parenchyma region from the smooth image to obtain a lung parenchyma mask; obtaining a lung parenchyma image based on the lung parenchyma mask and the smooth image mask; calculating multi-scale Hessian matrix eigenvalues on the lung parenchyma image; calculating a tubular structure enhancement response value according to the eigenvalues to obtain a multi-scale tubular structure enhancement image; performing connected domain analysis on the enhancement image, and screening out lung artery and vein candidate regions according to size and shape characteristics; and distinguishing the lung artery and vein in the candidate regions by using local gray distribution and morphological characteristics to obtain an extraction result.

The present disclosure relates to the technical field of medical images, and discloses a lung lesion identification method and device and an electronic device. The method comprises: acquiring a scan image of a patient's lung, identifying a pulmonary artery region and a pulmonary vein region of the lung in the scan image; acquiring a size parameter of each blood vessel in the pulmonary artery region and the pulmonary vein region, calculating a blood vessel feature of each blood vessel region according to the size parameter of each blood vessel in the pulmonary artery region and the pulmonary vein region; fusing the blood vessel feature of each blood vessel region with a previously acquired lung parenchyma structure feature of the patient's lung to obtain a fused feature; and inputting the fused feature into a previously trained classifier to identify a lung lesion evaluation result of the patient. The above method distinguishes the pulmonary artery and vein, quantifies the features, fuses the emphysema and airway multi-dimensional lesion indicators, and improves the comprehensiveness and accuracy of lung lesion identification. Meanwhile, the method does not require complex data support, simplifies the process, and reduces application costs.

The invention provides an application of 5, 6-EET as a predictive marker of triple negative breast cancer pulmonary metastasis, and 5, 6-EET promotes triple negative breast cancer pulmonary metastasis. And 5, 6-EET promotes lung metastasis of triple-negative breast cancer by enhancing the permeability of pulmonary vessels. The 5, 6-EET promotes TNBC cells to generate pulmonary parenchyma metastasis by enhancing the permeability of mouse pulmonary vessels, and the discovery helps people to understand the scientific significance of arachidonic acid metabolism reprogramming in the TNBC pulmonary metastasis process, clarifies the molecular mechanism of 5, 6-EET metabolism in the TNBC pulmonary metastasis process, and provides a potential reference index for predicting the pulmonary metastasis risk.

The present application belongs to the field of image processing, and discloses a lung parenchyma segmentation method combining Weber-Fechner law and semantic diffusion, comprising the following steps: processing an original lung three-dimensional CT image, cropping to a fixed size, and performing random enhancement; using the preprocessed image to train a lung parenchyma segmentation model combining Weber-Fechner law and semantic diffusion network, to obtain a lung parenchyma segmentation model; using the lung parenchyma segmentation model to predict the lung three-dimensional CT image, and outputting the predicted segmentation result. The present application is suitable for lung parenchyma segmentation based on three-dimensional lung CT images, and can effectively and accurately segment the lung parenchyma part from the CT image. The model has excellent generalization and robustness, and can exhibit excellent segmentation performance on fibrotic lung images.

The quality of a chest X-ray depends on the inspiration state of the patient being imaged. If the patient's lungs are not significantly inflated during the chest X-ray, tissue from surrounding organs can obscure the image and the lung parenchyma is not effectively shown. Therefore, it is up to the medical professional to ensure that the patient is in the proper posture and inspiration state at the point of image exposure. But this can be difficult for patients with chronic conditions. Therefore, this application discusses a means of assessing the inspiration state using the position of the ribs and diaphragm line in the X-ray image. Thus, an accurate estimate of the inspiration state can be automatically reported to the medical professional before the patient leaves the examination room, allowing a retake of the X-ray if necessary.

The present application relates to the technical field of medical image processing, in order to solve the technical problem of high false positive caused by the existing detection segmentation method, the present application discloses a CT image lung nodule automatic segmentation method and device based on mathematical morphology, including the steps of obtaining original data, lung parenchyma segmentation, mathematical morphology preprocessing, high signal region extraction, mathematical morphology processing, false positive nodule exclusion and three-dimensional reconstruction. The mathematical morphology processing step performs a mathematical morphology opening operation on the high signal region with a structure element radius similar to the maximum intrapulmonary vessel radius, obtaining a potential nodule image region. The false positive nodule exclusion step removes false positive nodules from the potential nodule image region through geometric features and threshold processing. Mathematical morphology operation is fast, and can realize fast lung nodule detection and segmentation operation. Geometric features and threshold processing can effectively remove most false positive objects.