62 results about "Lung lesion" patented technology

A method and a system are disclosed for labeling an anatomical point associated with a lesion in an organ such as a lung. The method includes: a segmentation of a vessel tree anatomical structure starting from an autonomously determined initial image point; labeling the vessel segments of the vessel tree segmentation with segment labels based on a priori anatomical knowledge, thereby creating an individualized anatomical model; receiving a user-specified image point having a location from a user and locating a nearby vessel structure; tracking along the vessel structure in a direction towards a root of a parent vessel tree until a prior labeled vessel segment is encountered in the anatomical model, and assigning the label of the encountered prior labeled vessel segment from the anatomical model as an anatomical location label of the user-specified image point.

Techniques for segmentation include determining an edge of voxels in a range associated with a target object. A center voxel is determined. Target size is determined based on the center voxel. In some embodiments, edges near the center are suppressed, markers are determined based on the center, and an initial boundary is determined using a watershed transform. Some embodiments include determining multiple rays originating at the center in 3D, and determining adjacent rays for each. In some embodiments, a 2D field of amplitudes is determined on a first dimension for distance along a ray and a second dimension for successive rays in order. An initial boundary is determined based on a path of minimum cost to connect each ray. In some embodiments, active contouring is performed using a novel term to refine the initial boundary. In some embodiments, boundaries of part-solid target objects are refined using Markov models.

The invention provides a lung lesion detection method and system, a storage medium, a terminal and a display system. The lung lesion detection method comprises the steps of acquiring a patient image marked with a lesion; identifying the marked area contour, and training the identified area contour to obtain key feature points; extracting a thoracic cavity image from the whole body image of the patient, and judging whether the extracted thoracic cavity image belongs to the thoracic cavity or not; if so, executing the next step; if not, re-extracting the thoracic cavity image; reading the extracted thoracic cavity image, converting pixel values of the thoracic cavity image, and genertaing a medical image file and a medical image with a mask; performing focus detection on the medical image with the mask through the key feature points of the focus; and mapping the detected lesions to the extracted thoracic cavity image to realize visualization of the lung lesion and form a lung 3D model. Amedical auxiliary means is provided for doctors, and the doctors are assisted to accurately diagnose the position of the lung focus in the image.

The invention provides a lung image segmentation method and device and lung lesion area identification equipment, and the method comprises the steps: converting a to-be-segmented lung image into a first binary image according to a preset gray threshold; performing negation processing on the first binarized image to obtain a second binarized image; performing hole filling on the second binarized image, and performing negation processing to obtain a third binarized image; removing an interference region in the third binarized image to obtain a first mask; filling the first mask to obtain a second mask; performing subtraction operation on the second mask and the first mask to obtain a lung region mask; multiplying the lung region mask and the to-be-segmented lung image to obtain a lung parenchyma image. According to the invention, the lung parenchyma image can be extracted rapidly and accurately and lung lesion area identification is carried out by using the three-dimensional image, so that doctors are assisted well and the working efficiency is improved.

The invention provides a lung detection method and device based on PET / CT image features. The method comprises the steps that the local image of a region corresponding to a lesion is acquired from a PET / CT image library as a training image; the PET / CT image library comprises the lung lesion images of multiple types of lesions; the training image is transformed and filtered to acquire a processed training image; the feature information of the processed training image is extracted, wherein the feature information comprises one or combination of texture feature information and color feature information; a lesion detection model is established according to the feature information; and a lung image to be detected is detected based on the lesion detection model to determine the type of the lesion in the lung image to be detected. An image processing technology is used to carry out lesion analysis and identification on a PET / CT image, which improves the accuracy and sensitivity of lesion identification.

The embodiment of the invention provides a lung focus statistical attribute obtaining method and device, electronic equipment and a storage medium. The method comprises the steps that a lung area in alung CT image sequence to be analyzed is extracted; determining a plurality of lesion areas in the lung area; and determining the focus statistical attribute of the lung CT image sequence based on the volume of each focus area in each layer of lung CT image of the lung CT image sequence. The embodiment of the invention provides a lung focus statistical attribute collection method and device, electronic equipment and a storage medium. Based on the volume of each lesion area in each layer of lung CT image of the lung CT image sequence, various types of lesion statistical attributes of the lungCT image sequence are determined, and accurate and diversified lung lesion quantitative analysis is realized.

The invention discloses a method for constructing a benign and malignant lung tumor prediction model. The method comprises the following steps that (1) a lung tumor patient sample is selected and computerized tomography (CT) is performed on the lung region of the lung tumor patient so as to acquire the corresponding CT image; (2) the CT image acquired in the step (1) is sketched and the lung lesion region is segmented so as to obtain the marked lesion region; (3) quantitative image features are extracted from the marked lesion region; (4) feature selection is performed by using the Lasso algorithm; and (5) the selected feature data act as the input, parameter optimization is performed on Logistic regression by using the gradient descent algorithm and finally the benign and malignant lung tumor prediction model is obtained by using Logistic training. The method for constructing the benign and malignant lung tumor prediction model is simple, short in time consumption and high in accuracyof the prediction model and can be applied to qualitative diagnosis of the benign and malignant lung tumors.

The invention provides an automatic segmenting method for lesion tissue in a lung CT image. The automatic segmenting method comprises the steps that the lung parenchyma CT image is searched for the minimum neighborhood gradient value of all points through a toboggan algorithm, the area of the initial growth point of the lung lesion is obtained according to the minimum neighborhood gradient value, and the initial growth seed point is determined according to the area of the initial growth point of the lung lesion; pixel grey level constraints and growth distance constraints are obtained according to the initial growth seed point, a lung lesion area is determined from the pixel grey level constraints and the growth distance constraints through an area growth method; boundaries of all layers of the lung lesion area are obtained according to the lug lesion area, boundary pixel points of adjacent layers in the lung lesion area are obtained in the central points of the boundaries of all the layers of the lung lesion area in the preset direction, the average distance difference value is obtained according to the boundary pixel points of the adjacent layers and the central point of the lung lesion area, and the pixel points exceeding the average distance difference value are horizontally slide to obtain segmentation images of the lung lesion tissue.

A method and a system are disclosed for labeling an anatomical point associated with a lesion in an organ such as a lung. The method includes: a segmentation of a vessel tree anatomical structure starting from an autonomously determined initial image point; labeling the vessel segments of the vessel tree segmentation with segment labels based on a priori anatomical knowledge, thereby creating an individualized anatomical model; receiving a user-specified image point having a location from a user and locating a nearby vessel structure; tracking along the vessel structure in a direction towards a root of a parent vessel tree until a prior labeled vessel segment is encountered in the anatomical model, and assigning the label of the encountered prior labeled vessel segment from the anatomical model as an anatomical location label of the user-specified image point.

An application method of a serum lipid biomarker in NSCLC early diagnosis includes the following steps: collecting serum samples of NSCLC patients, patients with benign lung lesions and normal people;pretreating the serum samples, and detecting lipid metabolism markers in each serum sample by utilizing a method of ultra-high performance liquid chromatography-quadrupole-time of flight mass spectrometry; screening NSCLC-related differential lipid metabolism markers through a method of multivariate pattern recognition analysis; screening out key metabolic pathways with highest correlation with the lipid metabolites through KEGG analysis and metabolic pathway analysis of NSCLC differential lipid metabolites; performing network analysis of "gene-enzyme-reaction-metabolite" of the NSCLC differential lipid metabolites, to obtain a network graph of the NSCLC differential lipid metabolites; and screening and obtaining the serum lipid biomarker for the NSCLC early diagnosis through integrationof the screening of the NSCLC differential lipid metabolism markers and analysis results of the metabolic pathways.

The invention discloses a lung anatomy position positioning algorithm based on a deep learning technology, which can accurately and quickly divide lung CT, and can simply, quickly and accurately realize automatic segmentation of lung lobes based on lung CT images, thereby realizing the anatomy position positioning of lung lesions. Compared with a traditional segmentation method, the method has theoutstanding advantages that (1) the process is simple, and the end-to-end segmentation mode does not need to pay attention to other processes; (2) the multi-stage and multi-output network architecture controls the network in different stages, so that the segmentation effect is better, and the segmentation precision can be ensured to the maximum extent through a semantic-based segmentation mode; and (3) the generalization ability is strong, and the data in the training process is enhanced, so that the model can learn different and diverse data, namely, the generalization ability of the segmentation model is ensured, meanwhile, the risk of over-fitting is also avoided to a certain extent, and the geometric deformation and illumination influence of CT (computed tomography) are insensitive when lung lobe division is performed on different CT.

The invention discloses a corona virus disease 2019 screening method and system based on deep learning. The corona virus disease 2019 screening method comprises the steps: detecting a lung lesion areaof CT by using a deep learning detection model, and conveying the lung lesion area of CT into a three-classification network, wherein three classifications comprise COVID-19, influenza A and non-infection symptoms; and through calculation processing, outputting a CT diagnosis result and a disease probability. According to the method, based on deep learning, characteristics of CT images are automatically learned to distinguish COVIDI-19, influenza A and healthy people, so that the method is high in accuracy, the overall accuracy of current testing reaches 86.7%, the diagnosis speed is high, and only 30-60 S is needed for one set of CT according to different slice numbers; and a user can upload a CT image file and calculate and output a CT diagnosis result and the disease probability through the corona virus disease 2019 screening system, so that operation is convenient, the speed is high, and the detection rate of COVID-19 is greatly increased.

The invention relates to an ultrasonic image quantitative evaluation method, which comprises the following steps of: 1, preprocessing an obtained lung ultrasonic image; 2, carrying out image segmentation on the lung ultrasonic image; 3, carrying out quantitative analysis index extraction on the lung ultrasonic image; and 4, carrying out multi-parameter conjoint analysis on the lung ultrasonic image. According to the method, parameters related to the pleura line, the B line and the real lung change are extracted by adopting a method for carrying out quantitative analysis on the ultrasonic image, then a multi-parameter conjoint analysis method is utilized, all quantitative analysis indexes are comprehensively utilized, and finally a lung lesion degree classification result is obtained. Therefore, a non-invasive / quantitative lung ultrasound image quantitative evaluation method is provided for clinic, and the method can be better applied to rapid lesion screening, grading diagnosis and illness follow-up visit of a large range of people and critically ill bedside monitoring.

The invention relates to a mycoplasma bovis and application thereof. A pathogen is determined to be the mycoplasma bovis through the steps of isolated culture of the pathogen, animal regression testing and 16S rRNA gene sequence determination and is named as a mycoplasma bovis MbovFJ1201 strain, and the preservation number is CCTCC NO: M2015772. The strain is inoculated to a culture medium for expanding cultivation, a culture is obtained and is inactivated, an ISA-206 adjuvant is added in proportion of 1:1 after inactivation, and mixing is performed to obtain an inactivated vaccine. The vaccine is good in targeting property and good in immune protection effect, can remarkably reduce lung lesions caused by mycoplasma bovis infection and improve the average daily gain and can achieve the good effect of preventing and controlling related diseases of the mycoplasma bovis.

The invention belongs to the medical image segmentation technology field and discloses an automatic lung medical image segmentation method. According to the method, the pixel gray constraint and the growth distance constraint are acquired according to an initial growth seed point, and a lung lesion region is determined from the pixel gray constraint and the growth distance constraint, and the lunglesion region is smoothed to accurately acquire a segmented image of the lung lesion tissue. The method is advantaged in that the initial lung shape can be relatively excellently acquired, over-segmentation during subsequent adjustment (for example, recognizing the spine and the stomach cavity as the lung region) can be avoided, under constraints of an active shape model, the lung region on the X-ray chest can be accurately segmented to provide valuable data for clinical or computer analysis.

The invention discloses a lung biopsy method guided by virtual positioning CT, which is characterized in that: the method includes: (1) image simulation before puncture; (2) simulation-guided puncture; (3) CT verification to complete the puncture. The virtual positioning CT-guided lung biopsy method uses electromagnetic positioning methods combined with CT images to form a virtual image; the position changes of the body surface magnetic electrode positioning marks under different respiratory motion states, and the dynamics of virtual lung lesions moving with respiratory motion The image can guide the lung puncture biopsy needle with the magnetic positioning mark on the tip to accurately complete the lung puncture, and eliminate the influence of breathing movement on the lung puncture positioning. The lung biopsy method under the guidance of virtual positioning CT uses several electromagnetic marks to assist in the positioning of lung lesions and improve the accuracy of puncture. puncture.

The invention discloses a method for calculating the proportion of a new coronal pneumonia lesion area based on deep learning, which belongs to the technical field of lung measurement, and comprises the following steps: carrying out normalization processing on an original CT image set to adapt to data input of a deep learning model; respectively inputting CT image data in the training set into twonetwork learning models of 2 DUnet and 2.5 DUnet, and predicting a binary mask of a lung lesion area and a binary mask of a whole lung area; calculating the similarity between a binary mask predictedby the training set and a real label mask, and selecting an optimal network learning model; and by using the optimal network learning model, predicting lung lesion area masks and lung whole area masks for the CT images in the training set, and calculating the proportion between the lesion area masks and the whole area masks. According to the method, the lung lesion area and the effective mask ofthe whole lung are automatically segmented by utilizing a deep learning technology, so that the volume ratio of the lesion area is rapidly and accurately calculated.

The invention belongs to the technical field of machine learning, and particularly relates to a lung medical image analysis method, device and system. The lung medical image analysis method comprises the steps of segmenting a lung field and a lung lesion area from an acquired lung medical image, calculating an ROI (Region of Interest) containing the lung field and the lung lesion area, and cutting an input picture for image recognition in the lung medical image according to the ROI. And inputting the input picture into a second-stage detection model, further extracting feature parameters, and obtaining a final lesion analysis result output by a preset semantic segmentation model. By means of the lung medical image analysis method, device and system, multiple lung lesions can be recognized and classified and judged at the same time, and the device is high in efficiency and accuracy of lung medical image analysis and has good application prospects.

The invention provides a preparation method, a formula and a use method of a bovine mycoplasma pneumonia inactivated vaccine. The preparation method of the bovine mycoplasma pneumonia inactivated vaccine comprises the following steps: 1, selecting diseased cattle which naturally infect mycoplasma pneumonia and is dying, taking diseased lungs, lymph glands and spleens to homogenize and removing precipitates and grease through filtering and centrifugation to obtain an antigen solution; 2, adding formaldehyde into the antigen solution to inactivate for 72 hours, adding 1,000 units of penicillin and 1,000 units of streptomycin into the antigen solution per millimeter and uniformly mixing to obtain an inactivated antigen solution; 3, mixing the inactivated antigen solution with an aluminum hydroxide adjuvant according to the proportion of 4:1 to obtain the inactivated vaccine. The vaccine prepared by the preparation method is safe in application, strong in pertinence and indeed in immune protection effect on mycoplasma causing bovine pleuropneumonia by infection, the lung lesion score of the infected cattle can be obviously reduced, the material weight ratio is improved, and the good effects of prevention and disease control can be achieved.

The invention discloses a CT-guided percutaneous lung puncture guide pre-positioning device. The device comprises flexible positioning pieces and connecting pieces. The flexible positioning pieces form a rectangular fence through the connecting pieces and can be freely bent, and the flexible positioning pieces are attached to the skin of a patient to be subjected to puncture by their gravity. Theflexible positioning pieces can be freely bent in the transverse direction and the longitudinal direction and can be attached to the patient's skin without moving easily, and the accuracy of positioning is guranateed; there is basically no distance between the flexible positioning pieces and the patient's skin surface, after CT scanning imaging, the distance between the flexible positioning piecesand the patient's lung lesion and the puncture angle can be easily observed, there is no large error in actual puncture operation, and thus accurate positioning for puncture is achieved.

The invention provides a semi-automatic segmentation method for sketching a regional growth lung tumor radiotherapy target region, and the method specifically comprises the following steps of S1, lesion automatic initial seed point selection characterized by obtaining lesion seed points from a lung parenchyma gradient image containing lesion through the step, and obtaining a lung parenchyma CT image gradient minimum value through calculation; and S2, final lesion position refinement characterized by carrying out the refinement of the final lesion position by determining a more accurate lesionboundary definition. By using the method provided by the invention, the steady, efficient and accurate lung lesion segmentation can be automatically realized.

The invention belongs to the field of medicine, and relates to a drug for treating acute lung injury and acute respiratory distress syndrome, wherein the active components of the drug is ganolucidic acid A or corosolic acid or a composition of ganolucidic acid A and corosolic acid, and the dosage form of the drug is one selected from an oral liquid preparation, a pulmonary inhalation preparation and an injection. According to the present invention, the drug can reduce the pulmonary edema of acute lung injury and acute respiratory distress syndrome, reduce lung hyaline membrane formation and other lung lesions, and easily improve the symptoms of acute lung injury and acute respiratory distress syndrome.

The embodiment of the invention provides a lung lesion area extraction method and device, electronic equipment and a storage medium. The method comprises: determining a lung image; inputting the lungimage into a focus detection model to obtain a focus detection result output by the focus detection model; inputting the lung image into a focus segmentation model to obtain a focus segmentation result output by the focus segmentation model; and determining a focus area extraction result of the lung image based on the focus detection result and the focus segmentation result. According to the method and device, the electronic equipment and the storage medium which are provided by the embodiment of the invention, the focus detection result is obtained through the focus detection model, the lesion segmentation result is obtained through the lesion segmentation model, automatic lesion region extraction is realized, and the lesion region extraction result of the lung image considering region extraction accuracy and extraction precision is obtained by combining the advantages of the lesion detection model and the lesion segmentation model while the lesion region extraction efficiency is ensured.

Techniques for segmentation include determining an edge of voxels in a range associated with a target object. A center voxel is determined. Target size is determined based on the center voxel. In some embodiments, edges near the center are suppressed, markers are determined based on the center, and an initial boundary is determined using a watershed transform. Some embodiments include determining multiple rays originating at the center in 3D, and determining adjacent rays for each. In some embodiments, a 2D field of amplitudes is determined on a first dimension for distance along a ray and a second dimension for successive rays in order. An initial boundary is determined based on a path of minimum cost to connect each ray. In some embodiments, active contouring is performed using a novel term to refine the initial boundary. In some embodiments, boundaries of part-solid target objects are refined using Markov models.

The invention belongs to the technical field of lung lesion image segmentation, and particularly relates to a lung lesion image segmentation method based on CovSegNet, and the method comprises the following steps: data collection, data preprocessing, model construction, model storage, and model evaluation. The data acquisition is used for acquiring various data sets from pulmonary infection, performing data annotation on images in the acquired data set, and constructing a data set required by model training; the data preprocessing is used for data division, normalization and image scaling, and data expansion is carried out; the model construction is based on a CovSegNet segmentation network model, training data are input, and a parameter model is constructed; the model saves the model after the loss function is not reduced any more; the model evaluation is used for evaluating the stored model through a plurality of evaluation indexes and knowing the related performance of the model.

The invention discloses a method for processing a lung lesion area image and a related product. The method comprises the following steps: acquiring three-dimensional image data of a lung lesion area,generating a tetrahedral mesh formed by connecting a plurality of vertexes according to the three-dimensional image data of the lung lesion area, determining a geometric characteristic value at the vertex by utilizing the voxel value at the vertex, and replacing the voxel value with the geometric feature value to realize extraction of the geometric features of the lung lesion area. According to themethod, the high-order geometrical characteristics are extracted from the lung lesion area image, so that richer characteristic information is contained, the intrinsic geometrical attributes of the lesion area image can be reflected, and subsequent further research is facilitated.

The invention relates to a primer for diagnosing lung lesions caused by chrysotile and man-made mineral fiber by using an RT-PCR method. The primer comprises a primer pair 1, a primer pair 2 and a primer pair 3 which are respectively used for amplifying miR-29a, miR-29b and miR-29c, and a base sequence is showed as SEQ ID NO.4-9. An miRNA amplification primer is designed on the basis of rat lung tissue pathological mechanism expressions by building a rat dust dying model, expression situations of miR-29 family members in dust dying rat lung tissues are detected, and an effective tool of early diagnosis and screening of health hazards caused by exposure of the chrysotile and the man-made mineral fiber is provided.

The invention relates to a traditional Chinese medicine prescription for treating pulmonary diseases, which comprises lapis chloriti, roasted ephedra, almond, schisandra, snakegourd peel and roasted licorice. Experiments prove that the traditional Chinese medicine prescription can obviously improve the pulmonary lesion and inflammatory reaction of a model rat with the chronic obstructive pulmonary disease at the acute exacerbation, so as to obviously reduce the contents of main inflammatory markers in the serum of the model rat, and simultaneously can promote the trachea repair of the model rat so as to prevent the occurrence and development of trachea inflammation. Clinical researches show that the traditional Chinese medicine prescription has a good effect and a high effect taking speed when being used for treating empirical pulmonary diseases, such as accumulation of pathogenic heat in the lung and obstruction of the lung by phlegm; the good effect can be achieved within 3-10 days, and the total effective rate reaches 96.6%; the traditional Chinese medicine prescription especially has good curative effects on chronic intractable pulmonary diseases induced by pathogenic heat and stubborn phlegm; the traditional Chinese medicine prescription does not have toxic or side effects; and the pulmonary diseases can not recur.

The embodiment of the invention provides a lung lesion analysis method and device, electronic equipment and a storage medium, and the method comprises the steps: inputting a to-be-analyzed chest imageinto a lesion positioning model, and obtaining a lung lesion positioning result of the chest image outputted by the lesion positioning model; and inputting the fused image determined based on the chest image and the lung focus positioning result of the chest image, or inputting the chest image and the lung focus positioning result of the chest image into a focus analysis model to obtain a lung focus analysis result of the chest image output by the focus analysis model. The lung lesion analysis result can comprehensively cover all lung lesions including tiny lesions and atypical lesions, and the reliability and accuracy of lung lesion analysis are ensured.