41 results about "Pulmonary parenchyma" patented technology

The embodiment of the invention provides an emphysema CT image segmentation method based on multi-feature dynamic fusion and boundary perception, and is applied to the field of medical lung CT image segmentation, the method obtains an original image by obtaining an emphysema CT image and preprocessing the emphysema CT image, and the preprocessing comprises extraction and standardization of a lung parenchyma region of interest; inputting the original image into the trained emphysema CT image segmentation model for segmentation to obtain an image segmentation result; wherein the emphysema CT image segmentation model comprises an encoder and a decoder, the encoder comprises a convolutional neural network branch, a Transform branch and a dynamic fusion module, the convolutional neural network branch is parallel to the Transform branch, and the decoder comprises an up-sampling layer and a boundary sensing module. The method improves the accuracy and reliability of the image segmentation result of the emphysema CT image.

The invention discloses a lung three-dimensional reconstruction method and system for intraoperative positioning, and the method comprises the steps: processing a lung CT image in a DICOM format through an improved lung parenchyma segmentation algorithm, precisely extracting a lung structure through a global threshold method, connected region analysis and mathematical morphology processing, and then processing a mask generated through segmentation through a real-time smooth interpolation method, and through a dynamic parameter adaptation technology, accurate matching of a segmentation result and a gray value range of modeling data is ensured. According to the method, the problems of artifacts, redundant surfaces and gray level jump of the lung parenchyma area caused by separation of segmentation and reconstruction in a traditional method are avoided, full-process automation from data reading and lung parenchyma segmentation to three-dimensional modeling and visualization is achieved, meanwhile, a user-friendly interaction interface is designed, and a convenient tool is provided for intraoperative navigation.

The invention discloses an active / inactive pulmonary tuberculosis recognition system based on an improved 3D network, and the system comprises an image feature obtaining module which is used for obtaining pulmonary tuberculosis CT chest image features; the data preprocessing module is used for carrying out data preprocessing on the obtained pulmonary tuberculosis CT chest image features; the image segmentation module is used for segmenting the preprocessed pulmonary tuberculosis CT chest image features to obtain pulmonary parenchyma image features, and an adopted segmentation model is a 3D ResUNet segmentation model; the image classification and recognition module is used for performing prediction and classification on the lung parenchyma image features after image segmentation; wherein the adopted image classification model 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, image output features are processed by adopting grouping convolution and channel shuffling, the types of active and inactive pulmonary tuberculosis are predicted, and confidence scores of the model are generated; the CT image classification accuracy of the model can be improved.

According to the chronic obstructive pulmonary disease grading system and method based on the X-ray chest radiograph, the original X-ray chest radiograph is obtained, and the original X-ray chest radiograph is preprocessed; a conditional generative adversarial network is adopted to separate the preprocessed original X-ray chest radiograph, and a bone suppression image and a bone tissue feature image are obtained; inputting the bone tissue feature image into the constructed double-branch deep neural network to obtain a pulmonary parenchyma feature map and a rib feature map; obtaining a clinical variable, preprocessing the clinical variable, performing cross-modal fusion on the preprocessed clinical variable, the lung parenchyma feature map and the rib feature map, and generating a fusion feature vector; processing the fusion feature vector by combining a regression-classification output header model to obtain an FEV1% predicted value and a GOLD staging result; a conditional generative adversarial network, a double-branch deep neural network, cross-modal fusion and a joint regression-classification output head model are introduced, and low-cost, low-radiation and high-universality GOLD automatic grading can be realized.

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 present invention relates to the fields of artificial intelligence and digital medical technology, and provides a lung image segmentation method, apparatus, storage medium, and computer equipment. The method comprises: constructing a lung nodule segmentation model based on a fully convolutional neural network model using a densely connected hybrid dilated convolution module and a hierarchical attention mechanism; training the lung nodule segmentation model using lung parenchyma image samples as input and lung nodule segmentation images of the lung parenchyma image samples as output to obtain a trained lung nodule segmentation model; obtaining a lung image to be processed, segmenting the lung image using a lung parenchyma segmentation algorithm to obtain a lung parenchyma image; and obtaining a lung nodule segmentation result for the lung image using the trained lung nodule segmentation model based on the lung parenchyma image. The above method can effectively improve the segmentation accuracy of lung nodules.

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.

The present disclosure is a telescopic endobronchial stem cell cultivation catheter that comprises a segment catheter (1), a terminal catheter (2), and a respiratory catheter (3) ensuring that ensures the prevention of the progression of COPD and provides early treatment before it progresses to advanced stages, allows the increase of the number of reduced lung parenchyma by means of its inoculation feature in advanced COPD stages, provides the removal of metaplastic cells in the bronchial walls in the application area with the rhythmic inflation-deflation movement by means of the balloons (1.2, 2.2, 3.2) and reduces the risk of future cancer formation, and increases respiratory ventilation by expanding narrowed terminal bronchioles (11) and increasing air flow to the respiratory bronchioles (12).

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.

The invention discloses a lung parenchyma extraction method, device and equipment based on a CT image, relates to the technical field of medical image processing, and can improve the accuracy of lung parenchyma region extraction. The scheme comprises the following steps: acquiring an axial CT image sequence; converting the axial CT image sequence into a coronal CT image sequence; three continuous frames of images are selected from the coronal CT image sequence to form three channels of RGB images, and the RGB images are obtained; determining a first lung area according to the pixel value of the RGB image; after morphological processing and hole filling are carried out on the first lung region, a region in a lung parenchyma boundary is extracted, and a second lung region is obtained; performing image segmentation processing on the second lung region to obtain a lung segmentation region; and generating a lung parenchyma region based on the lung segmentation region and the corresponding coronal CT image.

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.

The present disclosure is a telescopic endobronchial stem cell cultivation catheter that comprises a segment catheter (1), a terminal catheter (2), and a respiratory catheter (3) ensuring that ensures the prevention of the progression of COPD and provides early treatment before it progresses to advanced stages, allows the increase of the number of reduced lung parenchyma by means of its inoculation feature in advanced COPD stages, provides the removal of metaplastic cells in the bronchial walls in the application area with the rhythmic inflation-deflation movement by means of the balloons (1.2, 2.2, 3.2) and reduces the risk of future cancer formation, and increases respiratory ventilation by expanding narrowed terminal bronchioles (11) and increasing air flow to the respiratory bronchioles (12).

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.

The invention discloses an RT-DETR training method for pulmonary nodule detection, and relates to the technical field of medical and industrial combination. The RT-DETR training method for pulmonary nodule detection comprises the steps of firstly obtaining an original data set from an LUNA16 data set, then performing normalization and slicing on a CT image in the original data set, performing segmentation by using a K-means algorithm to generate a pulmonary parenchyma mask and VOC data to generate a required data set, and performing random distribution on the data set; a light-weight LSNet module is introduced to replace an original model Backbone, tiny textures are strengthened while a receptive field is expanded, an EDFFN is adopted to replace a two-layer feed-forward network in an original model feature interaction module, high-value information is reserved through frequency domain gating, and artifacts are suppressed; and training and testing the improved model by using a randomly distributed data set. The improved method can effectively, quickly and accurately detect the pulmonary nodules in the lung CT image.

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.

The invention relates to the field of medical image processing, in particular to an interstitial lung disease image diagnosis system fused with a generative adversarial network, which comprises a data preparation module for acquiring chest CT image data and carrying out pulmonary parenchyma segmentation and lung lobe segmentation, a preprocessing module for adjusting the interval between image layers and intercepting a region of interest to form a CT data set, and a processing module for processing the CT data set; the HRCT image enhancement network module generates an adversarial network architecture with a 3D condition and generates a high-resolution lung CT image with a layer thickness of 0.3 mm, the interstitial lung disease segmentation module uses a U-net network to carry out ground glass shadow and honeycomb change segmentation, and the lesion feature decoupling module carries out spatial feature extraction based on a graph convolutional network and carries out lesion classification. The diagnosis module identifies focus classification based on an interstitial lung disease classification network, generates an adversarial network through a 3D condition, and converts a common low-resolution CT image into a high-resolution CT image, so that common CT equipment has the diagnosis capability close to HRCT, and the equipment cost is greatly reduced.

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 application discloses a method, device, and apparatus for extracting lung parenchyma based on CT images, which relates to the field of medical image processing technology and can improve the accuracy of lung parenchyma region extraction. The scheme includes: acquiring an axial CT image sequence; converting the axial CT image sequence into a coronal CT image sequence; selecting three consecutive frames of images from the coronal CT image sequence to form three channels of an RGB image, thereby obtaining an RGB image; determining a first lung region based on the pixel values ​​of the RGB image; performing morphological processing and cavity filling on the first lung region, extracting the region within the lung parenchyma boundary, thereby obtaining a second lung region; performing image segmentation processing on the second lung region, thereby obtaining a lung segmentation region; and generating a lung parenchyma region based on the lung segmentation region and the corresponding coronal CT image.

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.