52 results about "Lung lesion" patented technology

The invention relates to a lung focus medical image segmentation method based on graphics and text information and knowledge embedding. The method comprises the following steps: acquiring a lung medical image of a patient and a corresponding clinical diagnosis report; preprocessing the lung medical image to obtain an enhanced image; inputting the lung medical image and the clinical diagnosis report into the medical visual language model to obtain a focus prompt embedding vector; and inputting the lung medical image, the enhanced image and the focus prompt embedding vector into the medical image segmentation model to obtain a lung focus region segmentation image. By adopting the method, the lung focus can be quickly positioned by the segmentation model through the focus prompt embedding vector, the interference of a non-target area is reduced, and the segmentation accuracy and the target concentration are improved.

The invention relates to a segmentation model based on a CNN and Transform parallel double-branch structure, and belongs to the technical field of medical data prediction. The method comprises the following steps: acquiring a CT image, and preprocessing the CT image by executing windowing processing and contrast limited adaptive histogram equalization; extracting features of lung lesions in the preprocessed CT image through a parallel double-branch structure; inputting the extracted features into a cross enhancement fusion module, and performing complementary fusion on the features through dynamic weight distribution to obtain fused features; the fusion features are input into a multi-scale context information extraction module, and lesion boundary sensitivity is enhanced through cavity convolution of different expansion rates; the encoder features and the decoder features are fused through jump connection, and a segmentation result is output after resolution is recovered based on up-sampling; and optimizing model training by adopting a weighted loss function. Accurate segmentation of the lung lesion in the pulmonary tuberculosis CT image is realized, and clearer and more accurate lesion area information can be provided.

The invention relates to the technical field of medical imaging, and discloses a peripheral lung cancer pleural invasion evaluation system based on ultrasonic targeted radiography, comprising: a double-frequency ultrasonic probe configured to independently work at different frequencies to realize depth imaging and high-resolution imaging of lung tissues and suitable for different types of lung lesions; the signal processing module can receive, analyze and process echo signals transmitted by the ultrasonic probe, generate images in real time and extract feature information; and the dynamic motion compensation module is used for automatically adjusting the emission time sequence and parameter setting of the ultrasonic signal based on the real-time breathing motion state of the patient. By adopting the design of the double-frequency ultrasonic probe and the core-shell structure, high-resolution imaging and depth detection of lung tissues are realized. By dynamically adjusting the thickness of the probe shell to be matched with the frequency, the system can adapt to complex tissue environments under different physiological conditions, and image definition and stability are ensured.

The invention discloses application of a neutralizing antibody of oncostatin M in preparation of a medicine for treating bronchial pulmonary dysplasia. The application proves that the intrauterine inflammation can cause BPD-like lung lesion to the filial generation mouse, and the OSM expression level in the mouse lung tissue one day after the intrauterine inflammation filial generation is grown is obviously higher than that of a control group; the OSM level of the BPD group is higher than that of the non-BPD group in the umbilical blood sample of the premature infant; in-vitro experiments show that the OSM treatment can cause lung epithelial cell injury; by dripping a recombined OSM neutralizing antibody into the nose of a newborn mouse, down-regulation of the OSM level in the lung of the mouse is realized, filial generation lung injury induced by the intrauterine inflammation can be repaired, and the OSM can be used as a treatment target of the BPD caused by the intrauterine inflammation.

The present invention provides a flexible biopsy forceps with a hollow channel for real-time biopsy of lung lesions, comprising an insertion portion having a hollow channel capable of accommodating a medical device for image-guided imaging; a gripping portion disposed at the distal end of the insertion portion, comprising a first metal groove and a second metal groove capable of interlocking to form a space for accommodating a biopsy specimen, while forming an opening at the distal end to allow the medical device to pass through; an operating portion disposed at the proximal end of the insertion portion and connected to the gripping portion via a connecting device; the operating portion capable of driving the first and second metal grooves to pivot. The present invention can meet the needs of real-time lung biopsy under the guidance of radial bronchial ultrasound or confocal laser endoscopic probes, improve the diagnosis rate of peripheral lung lesions, avoid radiation exposure of medical workers and patients, and provide high-quality pathology / microbiology test samples for later treatment.

The present application relates to the technical field of biological medicine, and discloses inhalable aptamer modified molybdenum disulfide nanoflower compound and application thereof.The compound comprises a molybdenum disulfide nanoflower core, a dendritic polylysine modification layer attached to the surface of the molybdenum disulfide nanoflower, doxorubicin loaded on the molybdenum disulfide nanoflower and / or the dendritic polylysine modification layer, and AS1411 aptamer combined on the outer surface of the dendritic polylysine modification layer by electrostatic assembly.The compound can be delivered to a lung lesion by atomization inhalation or aerosol inhalation, and undergoes responsive structural change under the action of hydrogen peroxide in a tumor microenvironment, generates active oxygen, and promotes the release of doxorubicin, so as to realize the synergistic antitumor effect of chemotherapy and chemical dynamic therapy.The compound has good colloidal stability, drug loading capacity, active targeting ability and lung local delivery potential, and can be used for preparing inhalation preparations or local administration preparations for treating lung cancer.

The invention provides a novel vaccine adjuvant and application of the novel vaccine adjuvant in preparation of the vaccine adjuvant. The BCG-PSN and vaccine induced RBD specific IgG antibody and neutralizing antibody level are equivalent to those of an aluminum adjuvant, the BCG-PSN and vaccine induce Th1 biased T cell reaction, the induced T cell response level is obviously higher than that of the aluminum adjuvant, and K18-hACE2 mice are protected from being affected by Delta variant induced lung lesions. As a vaccine adjuvant, BCG-PSN has wide compatibility and safety, and has no toxic or side effect.

A passive lung simulator device is provided. It includes a casing or box that includes a first lung simulator balloon; an air collector coupled to one end of the first balloon; a first set of servo valves, arranged in series, connected to the air collector via air flow conduits; and a connection element for a mechanical ventilator. The servo valves are configured to independently recirculate the air flow passing through them to the air collector, expanding the balloon. It also includes a first set of cams to be actuated by a servomotor to modify the compliance or capacity of the balloon simulator through the rotation of the first set of cams; and a communications module connected to the first set of servo valves and the first set of cams, with wireless connection to a remote computing device to receive instructions to simulate different pulmonary pathologies.

The application provides a deep granular unsupervised learning method for long-tailed distribution lung cancer subtype identification, comprising the following steps: S10, preprocessing lung lesion image data set, and generating two different enhanced views for each sample to obtain two sample image data sets; S20, using a pre-trained deep neural network to extract and normalize features of the two sample images to obtain sample feature vectors; S30, training using deep granular unsupervised learning, and unsupervised optimizing features based on the granular structure to improve feature separability under long-tailed distribution; and S40, obtaining final clustering results using the Kmeans method after training. The scheme is suitable for long-tailed distribution situations with significant differences in the number of samples of each subtype in the lung cancer subtype identification task, can improve the deep clustering effect for long-tailed distribution data, and provides reliable classification basis for the auxiliary diagnosis of lung cancer subtype identification.

The present invention relates to a guide sheath for peripheral bronchial lesion treatment, comprising a side tube for saline infusion, and injects physiological saline, which has been injected for peripheral bronchial dilation and access, through the side tube so that the physiological saline can efficiently reach a peripheral lung lesion as the physiological saline is injected through the side tube without insertion and removal of the guide sheath as in a conventional procedure, such that the precision and efficiency of a bronchoscopy procedure for diagnosing the peripheral lung lesion can be improved. In a conventional procedure, cold physiological saline or epinephrine for hemostasis could be administered after removal of the guide sheath and biopsy forceps, but the side tube of the guide sheath can administer a solution that assists hemostasis immediately after biopsy such that reduced side effects after the procedure and improved safety for the patient can be expected.

The invention discloses a lung rehabilitation respiratory training device combining traditional Chinese medicine and western medicine, relates to the technical field of rehabilitation training equipment, and aims to solve the problems of insufficient collaboration, deficiency of individualization and low system integration degree in the prior art. The device comprises a seat, a pedaling piece, a pushing and lifting rod and a breathing assembly, the breathing assembly comprises a traditional Chinese medicine box arranged on a seat backrest through a connecting rod, a breathing mask is arranged above the traditional Chinese medicine box, and a breathing mouth piece is arranged on the inner side of the breathing mask; the sealing connecting pipe is arranged between the traditional Chinese medicine box and the breathing mask; the respiratory capacity display tube is connected to the sealing connecting tube and connected with the traditional Chinese medicine box through a linkage assembly. According to the device, through a mechanical linkage structure, the inspiration action and the medicine mist release of a patient are accurately synchronized in time, it is ensured that quantitative traditional Chinese medicine mist is released at the moment that the inspiration force of the patient is maximum and the lung is expanded most sufficiently, medicine can directly reach the focus of the lung along with deep inspiration airflow, and the synergistic effect that most effective treatment is conducted at the best time is achieved.

The utility model relates to a medical auxiliary instrument. The utility model aims to provide a 3D printing type lung model for doctor-patient communication. The 3D printing type lung model comprises a lung model main body formed through 3D printing according to lung data of a patient; the lung model main body comprises a hollow lung lobe body formed by splicing two mold flaps, a trachea body formed on the lung lobe body in a heterochromatic 3D printing manner, and a focus body formed on the lung lobe body and / or the trachea body in a heterochromatic 3D printing manner; the lung lobe body is further provided with at least one hollow observation opening used for observing a focus body. According to the utility model, actual lung data 3D printing forming of a patient is adopted, the lung focus space structure of the patient can be fully and visually displayed, and accurate communication between a doctor and the patient is facilitated; 3D printing is conducted on the lung lobe body, the trachea body and the focus body through different colors, and the whole lung and the structure of the lung of the patient can be displayed in a layered mode more clearly.

The application discloses a lung three-dimensional reconstruction method and device, a terminal equipment and a readable storage medium. The method comprises the following steps: acquiring N two-dimensional images of a lung; generating a tubular organ overall point cloud based on the N two-dimensional images by using a first generator; generating an artery point cloud, a vein point cloud and a trachea point cloud based on the N two-dimensional images by using a second generator; generating a lung segment point cloud based on the N two-dimensional images by using a third generator; and three-dimensionally reconstructing the lung by using the tubular organ overall point cloud, the artery point cloud, the vein point cloud, the trachea point cloud and the lung segment point cloud. The application can quickly provide a three-dimensional image of the lung as a diagnosis basis for inexperienced doctors, effectively avoids the influence of the lung lesion diagnosis process on the doctors' subjectivity, improves the lung lesion diagnosis efficiency and the accuracy of the lung lesion diagnosis.

A passive lung simulator device is provided. It includes a casing or box that includes a first lung simulator balloon; an air collector coupled to one end of the first balloon; a first set of servo valves, arranged in series, connected to the air collector via air flow conduits; and a connection element for a mechanical ventilator. The servo valves are configured to independently recirculate the air flow passing through them to the air collector, expanding the balloon. It also includes a first set of cams to be actuated by a servomotor to modify the compliance or capacity of the balloon simulator through the rotation of the first set of cams; and a communications module connected to the first set of servo valves and the first set of cams, with wireless connection to a remote computing device to receive instructions to simulate different pulmonary pathologies.

The invention belongs to the technical field of biology, and particularly relates to application of an Mgst2 gene serving as a target to preparation of a product for treating rheumatoid arthritis related interstitial lung diseases. According to the invention, it is found for the first time that Mgst2 can be used as a biomarker for treatment of rheumatoid arthritis related interstitial lung diseases, targeted knock-down is carried out on Mgst2 in neutrophils through an AAV9-shRNA vector (AAV9-shRNA-Mgst2) driven by a Cd11b promoter, and lung lesion progress can be effectively relieved by inhibiting NET formation. The Mgst2 inhibitor provided by the invention can directly intervene in the occurrence and development process of diseases from a molecular level, and has the advantages of accurate effect, remarkable curative effect, low side effect and the like. Compared with a traditional non-specific treatment mode, the product takes effect only aiming at specific molecular targets, damage to normal cells and tissues is remarkably reduced, and therefore the risk of toxic and side effects is reduced.

The application discloses an aerosol inhalation type LNP composition for treating lung diseases and a preparation method and application thereof. The composition comprises an aerosol stabilizer and a surface coupled Anti-CD3 antibody lipid nanoparticle, and the surface coupled Anti-CD3 antibody lipid nanoparticle internally loads a CAR-mRNA targeting FAP. The application improves the efficiency of LNP targeted binding to T cells by coupling CD3 antibodies to LNP, and the LNP can significantly improve the in-vivo reprogramming efficiency of mouse T cells by coupling CD3 antibodies. The application administers the antibody coupled LNP by aerosol inhalation, and compared with common intravenous injection, the lung lesion accumulation of the LNP is improved, so that the treatment effect of pulmonary fibrosis is effectively improved.

The invention discloses a medical equipment intelligent management method and system based on data analysis, relates to the technical field of information processing management, and is used for solving the problem of low accuracy and intelligence of an analysis result caused by processing a lesion area according to a fixed rule and processing newly generated image data according to a preprocessing strategy. Comprising the steps of collecting historical medical image data of a CT machine, obtaining lung lesion images by recognizing lesion areas, performing area division on the images, analyzing lesion degrees of different sub-areas respectively, calculating corresponding lesion coverage degrees, and further establishing a fuzzy rule preprocessing model; according to the method, the preprocessing strategy can be dynamically adjusted, the efficiency and accuracy of lung lesion analysis are improved, updating of the preprocessing library is achieved through comparison and input of the new strategy, and therefore intelligent management of medical equipment is achieved, and diagnosis accuracy is improved.

The invention belongs to the technical field of medicines for treating rheumatoid arthritis complications, and particularly relates to a traditional Chinese medicine composition for rheumatoid arthritis interstitial pulmonary lesion as well as a preparation method and application of the traditional Chinese medicine composition. The traditional Chinese medicine composition comprises ginseng, astragalus membranaceus, prepared rehmannia root, schisandra chinensis, radix asteris, white mulberry root-bark, angelica sinensis, eclipta, radix glehniae, salvia miltiorrhiza, turmeric, exocarpium citri rubrum and liquorice. The traditional Chinese medicine composition has the effects of regulating qi and blood and treating both symptoms and root causes, is suitable for the symptoms of lung arthralgia, deficiency of both qi and yin and stasis of veins and collaterals, can obviously relieve the lung function of patients with rheumatoid arthritis interstitial pulmonary disease, reduces the symptom scores of shortness of breath, dry cough and progressive dyspnea, and improves the curative effect. And the progress of RA-ILD can be effectively inhibited by reducing macrophage apoptosis, activating and proliferating myofibroblasts and inhibiting MMT.

The invention provides a dry powder inhalation preparation taking enoxone as an active ingredient. The preparation is small in particle size, high in lung delivery efficiency, small in dosage and capable of remarkably improving the medication compliance of patients. The dry powder inhalation preparation can significantly reduce the level of white blood cells in pulmonary alveolar lavage fluid of a bronchial asthma rat model, improve the lung function and the lesion degree of trachea, bronchus and lung, and has an obvious treatment effect on bronchial asthma.

The invention provides a lung lesion automatic detection and diagnosis method based on a CT image, and relates to the field of medical image auxiliary diagnosis, and the method comprises the steps: S1, carrying out the multi-modal feature fusion and segmentation of an input CT image lung region; s2, detecting the pulmonary nodules based on dynamic self-adaptive expansion convolution; s3, quantifying the size of the pulmonary nodule in combination with the multi-modal features and the improved Snakes model; s4, performing dynamic tracking by adopting a space-time dynamic tracking module; s5, respectively extracting multi-dimensional features of the nodules by a feature extraction module, and providing input for a diagnosis decision; and S6, outputting benign / malignant diagnosis results by adopting the clinical diagnosis model. The method can accurately identify the position of the pulmonary nodule and judge the size of the nodule, thereby completing auxiliary diagnosis of the pulmonary nodule, and avoiding the problems of low efficiency, large human subjective factors, low accuracy and the like caused by excessive dependence on manpower.

A lung cancer chemoprevention drug delivery platform comprises a Janus nanoparticle comprising at least two chemopreventive agents for preventing / minimizing lung cancer or preventing recurrence of treated lung cancer. Further, an aerosolized composition is provided that comprises (a) at least one Janus nanoparticle configured to be aerosolized; (b) a bioactive protein inhibitor; (c)a modulator of at least one proinflammatory mediator; (d) an immune checkpoint inhibitor; and (e) short interfering sequence of double stranded RNA (siRNA) to modify proteins aberrantly upregulated in premalignant lung lesions. In another variation, methods for generating a lung cancer chemoprevention drug delivery platform for inhalation by a subject diagnosed with premalignant lung lesion is provided, where the drug delivery platform comprising: (a) a Janus nanoparticle, (b) a bioactive protein inhibitor; (c) a modulator of at least one proinflammatory mediator; (d) an immune checkpoint inhibitor; and (e) siRNA to modify proteins aberrantly upregulated in premalignant lung lesions.

The present invention implements a lung analysis system based on a parameter response graph and image generation system. It consists of a data collection and management module, an image registration module, a controllable image generation module, a parameter response graph analysis module, and a disease progression assessment module. The data collection and management module interfaces with the hospital information system and CT image collection equipment; the image registration module receives a patient's biphasic CT scan image and generates a registered biphasic CT image; the controllable image generation module receives a patient's single inspiratory phase CT scan image as input and generates a registered expiratory phase CT scan image; the parameter response graph analysis module obtains multiple parameter response graph analysis and assessment results for assessing a patient's organic lung lesions; and the disease progression assessment module predicts a patient's lung function. This solves the problems of difficulty in collecting biphasic CT images and the lack of ability to assess a patient's disease progression, which are common with parameter response graph methods.

Providing sensory output indicating lung thickening due to congestion, infection, inflammation, and / or fibrosis in a subject are described. Sensor output signals are processed to detect areas of lung thickening and a sensory output device is controlled to generate and / or modulate sensory output for spatially localized areas of lung thickening. In some embodiments, the system uses two-dimensional video images from an ultrasound machine and generates an audio signal such as a “click” each time a B-line, the visual representation of lung edema or fibrosis, is detected on the image. During real-time ultrasound imaging of a patient's lung, the patient may hear multiple clicks with varying intensity and frequency depending on proximity to areas of lung thickening. This facilitates examination of the lung using diagnostic ultrasound with feedback that is heard rather than seen, with louder and more frequent clicks representing areas of more diseased lung.

This invention provides a method and network for segmenting cellular lung lesions based on ViT and contextual feature fusion, belonging to the field of image processing technology. The network of this invention can achieve higher precision segmentation of cellular lung lesions; it utilizes channel-mixing convolutional blocks to increase the interaction of information between different channels, fully extracting feature information of the lesion site; it employs a Transformer architecture as a feature connector between the encoder and decoder, enhancing the feature representation of global information and expanding the receptive field of the network; it uses a CFB module to fuse features from multiple stages, reducing the semantic gap between high-level and low-level features, and improving the segmentation accuracy of lesion sites and target edges; this invention is applied to cellular lung lesion segmentation.

The present invention relates to a method of identifying a pre-invasive lung lesion in an individual that will progress to an invasive lung cancer involving determining the presence or absence of a molecular signature.The present invention also relates to a method of treating a pre-invasive lung lesion and / or treating and / or preventing an invasive lung cancer in an induvial comprising involving determining the presence or absence of a molecular signature.The present invention further relates to a molecular signature, and uses thereof, for identifying whether or not an individual has a pre-invasive lung lesion that will progress to an invasive lung cancer.

The application provides a lung CT image correlation analysis method, comprising: acquiring lung multi-modal images, including computer tomography images and positron emission tomography images, and performing denoising, enhancement and standardization pretreatment on the original images according to the imaging principles and image characteristics of different modalities; extracting a lung lesion region of interest from the registered multi-modal images, delineating and segmenting the lesion, and quantitatively analyzing the volume and shape geometric morphological characteristics of the lesion; based on the therapeutic effect, analyzing the correlation between the imaging features and the prognosis of the patient, estimating the recurrence and metastasis risk and survival period under different feature performances, combining the imaging features and the clinical indicators, constructing a therapeutic effect prediction model, and performing long-term individualized evaluation on the prognosis of the patient.

The invention relates to a nutritional formula food as well as a preparation method and application thereof, and the food composition comprises the following raw material components in parts by weight: 1.0-5.0 parts of a protein component; 1.0 to 3.0 parts of a fat component; 1.0 to 3.0 parts of a carbohydrate component; 0.05 to 0.1 part of a compound vitamin group; 0.1 to 0.3 part of a composite mineral substance component; 0.01 to 0.07 part of an oil phase emulsifier component; 0.1 to 0.3 part of a water phase stabilizer / thickener component; 0.01 to 0.07 part of a functional nutrient component; 0.005 to 0.15 part of a flavoring agent group; 80 to 100 parts of purified water (carrier); according to the formula, macro nutrients and functional components are scientifically proportioned, so that the special nutritional requirements of patients suffering from lung injury after chronic obstructive pulmonary disease (COPD) and cystic fibrosis related lung lesion infection are met in a targeted manner.

The application discloses a honeycomb lung lesion segmentation method combining U-shaped convolution and PPCT, and belongs to the technical field of medical image segmentation. The method provided by the application obtains a honeycomb lung lesion segmentation result by using a CUPTNet, and the encoding-decoding structure of the CUPTNet network is optimized by using GCT and ConvMixer, so that the ability of the model to extract global context in the encoding stage is improved, the correlation between modeling feature channels is improved, and these information is efficiently mixed. In addition, a pyramid pooling channel Transformer module is used to improve a simple skip connection, and the module can effectively utilize semantic information in multi-scale channel features, so as to provide sufficient useful information for decoding work. Compared with the prior art, the method provided by the application has better honeycomb lung lesion segmentation effect.