29 results about "Lung region" patented technology

An ultrasound therapy device for generating ultrasound therapy. The ultrasound therapy device includes a wearable structure, ultrasound transducer units, a tightening mechanism, a memory, and a processor. The wearable structure is securable to a user to transmit the ultrasound to a target therapy area of a user including at least one of a kidney region, a lung region, and a lower limb of the user. The ultrasound transducer units are attachable and repositionable in the wearable structure to generate and deliver the ultrasound to the target region. The ultrasound transducer units are arranged in an array. The array of ultrasound transducer units is mechanically moved within the wearable structure and is in contact with a material to facilitate penetration of ultrasound into the user's body.

The invention discloses a respiratory support aided decision-making method and system, and the method comprises the steps: obtaining lung image data of a patient, and carrying out the preprocessing of the lung image data, so as to extract a lung region of interest; inputting the lung region of interest into a prediction model to obtain image quantitative analysis data including lesion information; acquiring clinical index data of the patient, and fusing the clinical index data with the image quantitative analysis data to generate respiratory support comprehensive evaluation parameters; and outputting respiratory support decision auxiliary information based on the respiratory support comprehensive evaluation parameters. The respiratory support aided decision-making method and system provided by the invention aim at realizing automatic and objective analysis of the lung image, intelligently fusing the analysis result with the clinical indexes, and providing quantitative decision-making support for use of a respirator.

The invention discloses a multi-airway leaflet lung mechanical ventilation system, and relates to the technical field of medical equipment, the multi-airway leaflet lung mechanical ventilation system comprises a controller, an air path module and a catheter module, the air path module is electrically connected with the controller, and a pipeline is connected with the catheter module; the conduit module is connected with the controller; the conduit module comprises a ventilation pipeline and a plurality of branch ventilation conduits, and the branch ventilation conduits are in pipeline connection with the gas path module; and a motion control module is arranged on the branch ventilation guide pipe and is connected with the controller. Independent ventilation of a plurality of lung areas is achieved under one device, refined ventilation treatment is conducted on different lung areas, meanwhile, real-time monitoring of ventilation conditions of different lung areas can be achieved, and the treatment effect of mechanical ventilation is improved.

A method includes receiving one or more radiological images of an anatomy of a patient. The method also includes identifying a boundary of different tissue types in the anatomy of the patient based at least partially upon the one or more radiological images. The method also includes identifying one or more regions within the boundary. The one or more regions include a lung region. The method also includes identifying healthy tissue and COVID-19 tissue in the lung region. The method also includes quantifying an extent of the COVID-19 tissue in the lung region by comparing an amount of the COVID-19 tissue in the lung region to an amount of the healthy tissue in the lung region. The method also includes classifying the extent of the COVID-19 tissue in the lung region into one or more of a plurality of COVID-19 classes.

The present application relates to the field of electrical impedance imaging, and discloses a regional lung perfusion delay time analysis method, an electronic device and a storage medium. A dynamic image of conductivity change caused by blood perfusion in a human thoracic cavity is obtained. A blood perfusion image of a heart region and a blood perfusion image of a lung region are separated. A reference curve of conductivity change of the heart region is obtained according to the dynamic image of blood perfusion conductivity change and the blood perfusion image of the heart region. A conductivity change curve of each pixel point in the blood perfusion image of the lung region is obtained according to the dynamic image of blood perfusion conductivity change and the blood perfusion image of the lung region. The conductivity change curve is divided by a sliding time window, and a regional lung perfusion delay time is calculated in each time window. The time resolution advantage of electrical impedance imaging technology is fully utilized, and the time delay of the time when the local blood volume of the lung reaches the maximum relative to the end of the ventricular diastole is reflected by calculating the regional lung perfusion delay time.

According to the three-dimensional lung ventilation imaging method and device, the lung ventilation condition of each lung area in the three-dimensional space can be presented, the operation efficiency is improved, the depth estimation of the three-dimensional lung is more accurate, the three-dimensional lung is not limited to orthogonality body position projection data of the normal position and the lateral position, and the three-dimensional lung ventilation imaging method and device are particularly suitable for bedridden patients. The method comprises the following steps: (1) inputting X-ray data of a normal position and an oblique position of a chest; (2) integrating the X-ray data of the normal position and the oblique position of the chest, matching the data of the normal position and the oblique position of the same breathing time phase, and mapping the two-dimensional data of the normal position and the oblique position into a three-dimensional space; (3) estimating a free deformation FFD parameter and a double-lung translation parameter by using the input data; (4) obtaining an optimal three-dimensional lung surface model estimation and a lung template number by using the parameters in the step (3); (5) voting according to the three-dimensional lung surface model estimation of each frame and the optimal lung template to obtain a global optimal lung template number; and (6) estimating three-dimensional lung ventilation parameters according to the sequential three-dimensional lung surface model.

Certain embodiments provide a method for controlling airflow in a lung of a respiratory system of a patient. The method generally includes placing a device in an airway passage, wherein the device comprises: an outer wall and an inner wall defining a lumen from a proximal end to a distal end of the device and changing a volume of the lumen over time.

This invention provides a method, electronic device, and storage medium for extracting the region of interest (ROI) of the aorta. The method includes segmenting a medical image to be extracted; obtaining the lower boundary location information of the lung region and the coordinate information of the minimum horizontal bounding rectangle based on a lung mask image; obtaining the physical distance information from the starting and ending image layers of the medical image to the lower boundary of the lung region based on the lower boundary location information of the lung region; obtaining the upper and lower boundary location information of the ROI of the aorta based on the physical distance information from the starting and ending image layers of the medical image to the lower boundary of the lung region; and extracting the ROI of the aorta based on the coordinate information of the minimum horizontal bounding rectangle and the upper and lower boundary location information of the ROI of the aorta. This invention can automatically and accurately extract the ROI of the aorta, which is not only low-cost but also highly efficient.

The present application relates to the technical field of biology, and discloses a method for rapidly evaluating pneumonia, especially COVID-19, based on artificial intelligence, which comprises the following steps: 1) obtaining lung region ultrasound images and circulatory volume ultrasound images of a subject, wherein the circulatory volume ultrasound images comprise left ventricular outflow tract ultrasound images, left ventricular long-axis section ultrasound images and inferior vena cava long-axis section ultrasound images; 2) inputting the lung region ultrasound images and the circulatory volume ultrasound images of the subject into a trained deep convolutional neural network model, wherein the trained deep convolutional neural network model comprises a trained lung ultrasound image scoring model and a trained circulatory volume ultrasound image scoring model, so as to obtain the evaluation result of pneumonia of the subject. The present application also discloses a trained deep convolutional neural network model suitable for pneumonia, especially COVID-19, a construction method of the trained deep convolutional neural network model, and a remote operation ultrasound robot comprising the trained deep convolutional neural network model.

The present application relates to the technical field of CT image analysis and processing, and discloses a method and device for predicting the severity of pneumonia, electronic equipment and a medium. The method comprises: collecting a three-dimensional lung CT image of a patient, pre-processing the three-dimensional lung CT image, and obtaining a corresponding two-dimensional CT lung region image; based on the two-dimensional CT lung region image, performing hierarchical prediction through a prediction model, and outputting a first prediction result of each CT slice in the two-dimensional CT lung region image; based on the first prediction result of each CT slice, performing severity prediction through a preset logistic regression model, and outputting a corresponding severity weight; predicting the three-dimensional lung CT image, obtaining a corresponding pneumonia evaluation value, correcting the pneumonia evaluation value and the severity weight, and determining a final prediction result; thereby improving the accuracy of the severity prediction of pneumonia, and improving the performance and medical interpretability of the machine learning model.

The present disclosure relates to a method, device and equipment for determining the phase distribution of a cardiopulmonary region signal, the method comprising: collecting a target electrical impedance tomography signal synchronized with the mechanical movement of the heart of a subject from the electrical impedance tomography signals of the chest of the subject at multiple detection times; determining an electrical impedance static image of the chest of the subject according to the target electrical impedance tomography signal; determining a heart region of interest and a lung region of interest of the subject in the electrical impedance static image respectively; determining a peak pixel point image according to the electrical impedance time variation curve corresponding to the target pixel point in the lung region of interest; calculating the sum of the pixel points in the heart region of interest and the lung region of interest, multiplying the sum of the pixel points with each peak pixel point in the peak pixel point image one by one to obtain a phase distribution map of the cardiopulmonary region signal of the subject. The voltage signal synchronized with the mechanical movement of the heart can be corresponded with the spatial position, thereby accurately reflecting the phase distribution of the blood flow signal of the cardiopulmonary region of the subject.

The application discloses a severe patient acute lung injury evaluation system and method based on machine learning, relates to the field of acute lung injury evaluation, and comprises the following steps: acquiring chest multi-modal image data of a severe patient and performing standardized processing to generate a standard data set; dividing a lung region into structural blocks and extracting structural indexes, compensating for missing data through cross-modal space mapping or candidate block selection; identifying a modal conflict region and a structural mutation region to construct a scoring key region; after applying disturbance to screen an effective region, selecting a mean value or a weighted fusion strategy according to a consistency index; and combining dynamic weight to calculate a lung injury score and performing iterative optimization; the application can improve the identification accuracy of a key region of acute lung injury, and realizes accurate quantitative evaluation of the degree of lung injury.

This application provides a method and apparatus for region of interest (ROI) assessment, relating to the field of medical imaging technology. The method includes: acquiring chest images of a user at different times; performing the following for each chest image: extracting a lung region from the chest image, identifying anatomical landmarks in the lung region, determining the relative positions of different layers in the chest image based on the anatomical landmarks; determining the mapping relationship between different layers in different chest images based on the relative positions of the layers in each chest image; identifying a region of interest (ROI) within the lung region of each chest image; and generating a ROI assessment result based on the layer in which the ROI is located in the chest image and the mapping relationship between different layers in different chest images. This application can improve the accuracy of the assessment results.

The present application belongs to the field of intelligent medical treatment, and particularly relates to a critical patient Pendelluft automatic detection method based on electrical impedance tomography and artificial intelligence. The method comprises: acquiring EIT data of a lung region of a patient within a monitoring period; segmenting the lung region into multiple regions, and extracting EIT data of the multiple regions to obtain EIT signals of the multiple regions; obtaining a tidal resistance characteristic based on the EIT signals, the tidal resistance characteristic comprising: a regional tidal resistance amplitude difference and an adjacent regional tidal resistance amplitude difference; calculating an EIT ventilation characteristic based on the tidal resistance characteristic, the EIT ventilation characteristic being a swing breath; and judging whether the patient has Pendelluft based on the EIT ventilation characteristic. Based on real-time acquired EIT time series data, through processing of the time series data, an index reflecting whether Pendelluft exists and its severity is extracted, and based on real-time monitoring of Pendelluft, the clinical management of a clinician on a mechanically ventilated patient is assisted.

The present disclosure relates to a lung classification model training method, a lung image classification method and a device thereof. The training method comprises: performing regional feature extraction on each first lung image to obtain a first multi-region feature set, and performing regional dimension feature correlation analysis on the first multi-region feature set to obtain a first fusion feature set containing a non-redundant feature set and a correlation feature set; and performing iterative training of a lung classification model according to training label data and a plurality of first fusion feature sets, wherein the non-redundant feature set represents independent feature information with independent distinguishability of a plurality of lung regions, the correlation feature set represents complementary feature information between the plurality of lung regions, and the fusion feature set has precise representation capability of independent features of a single lung region and complementary features across regions, thereby breaking through the adaptation limitation of a fixed application scenario and improving the accuracy and robustness of the lung classification model.

This invention discloses a method for determining the lung recruitment endpoint using the PARDS ultrasound regasification score in children, relating to the field of pediatric critical respiratory support therapy. It solves the technical problem of existing technologies being unable to perform real-time dynamic zonal assessment of alveolar recruitment status in different lung regions, especially gravity-dependent areas, which easily leads to inadequate lung recruitment treatment. This invention performs standardized zonal ultrasound examination of the child's lungs during lung recruitment, employing a graded and quantified ultrasound regasification scoring system to assign values ​​to the lung ventilation level of each examined region. The total ultrasound regasification score is calculated by summing these values. With the core condition of continuously increasing PEEP and no further increase in the total score after plateau pressure, this invention can achieve objective and accurate determination of the lung recruitment endpoint, ensuring the adequacy and safety of lung recruitment treatment. It is applicable to the management of mechanical ventilation in children with acute respiratory distress syndrome.

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.

Disclosed are a visualization method for assisting medical image diagnosis comprising: acquiring first intensity values of first voxels in a lung region during inspiration, segmented from a chest computed tomography (CT) image acquired during inspiration, as first coordinate values of the first voxels; acquiring differences between second intensity values of second voxels, registered into the first voxels as voxels in the lung region during expiration segmented from a chest CT image acquired during expiration, and the first intensity values as second coordinate values of the first voxels; and visualizing a distribution of the first voxels by mapping the first voxels based on the first coordinate values and the second coordinate values.

The application provides a method and device for constructing a double-task lung collapse evaluation model, which comprises the following steps: obtaining lung images with different lung collapse degrees, and marking the collapsed lung region and the chest cavity background region; extracting the collapsed lung region image and marking the collapsed region and the non-collapsed region label; training a lung volume task segmentation module and a lung color task segmentation module based on the marked image; constructing a fusion evaluation module for obtaining the lung collapse evaluation result based on the segmentation result of the lung volume task segmentation module and the lung color task segmentation module; and obtaining the double-task lung collapse evaluation model based on the fusion evaluation module and the trained lung volume task segmentation module and lung color task segmentation module. The application solves the problem in the prior art that the lung collapse evaluation mainly depends on the subjective experience of doctors during surgery, lacks artificial intelligence assistance, and results in large differences in scoring results, which easily leads to misjudgment.

This invention discloses a vibration-type respiratory sputum clearance device, relating to the field of medical device technology. It includes a vest body. Multiple independent liquid-coupled vibration units are arranged on the inner side of the vest, corresponding to the upper and lower lobes of both lungs and the projected lung region on the back. Each liquid-coupled vibration unit includes a sealed liquid-sealed bag, and a vibration unit is disposed on the outer side of each sealed liquid-sealed bag. The sealed liquid-sealed bag is integrally embedded and fixed in a flexible interlayer on the inner side of the vest. The interior of the sealed liquid-sealed bag is filled with a vibration-transmitting liquid. The vibration-transmitting liquid filled in the sealed liquid-sealed bag of this invention, relying on its incompressible and highly fluid physical properties, can efficiently transmit and convert the high-frequency micro-vibrations generated by the double-layer piezoelectric sheet, forming a dual mechanical action of shallow loosening and deep oscillation, perfectly adapting to the sputum clearance needs of the soft tissues of the chest and back and the deep airways of the thoracic cavity.

A portable device that delivers knocks and vibrations to a lung region of a patient is disclosed. The apparatus comprises a support device (110) and at least one striking device (100). The support device (110) comprises at least one portion to receive and hold the striking device (100). The knocking device (100) includes a housing (102) having at least one actuator (104, 106) operably coupled to provide power to at least one contact head (108) for providing knocking and vibration to a patient. The contact head (108) is operable to press the chest by a depth in the range of 1 mm to 10 mm at a frequency in the range of 1.0 Hz to 16.67 Hz and a force in the range of 0.05 to 3 kg force (kgf) or in the range of 0.4903325 to 29.41995 Newton (N). The portable device is configured as a wearable or handheld device.

The invention discloses a chest CT deep screening optimization method and system based on artificial intelligence, and the method comprises the following steps: S1, collecting CT data, completing the resampling, normalization and lung region positioning, and generating standardized body data; s2, extracting a gray histogram, a radiation dose and a layer thickness, constructing a voxel condition vector, and generating a dynamic kernel parameter; s3, executing multi-scale Riesz wavelet decomposition according to the dynamic kernel parameters, and extracting a wavelet coefficient; s4, inputting the reversible block to complete affine transformation, introducing Gaussian noise, diffusing and denoising, and outputting a fine coefficient; s5, performing self-attention weighted fusion on the coefficient sequence to generate a weighted tensor; s6, inputting the teacher model to generate a soft label in a training stage, distilling to the student model, and outputting a sparse latent vector; and S7, inputting the diagnosis network in a reasoning stage, and outputting benign and malignant classifications, risk levels and screening suggestions. According to the method, multi-scale modeling and a distillation mechanism are fused, and the accuracy and the intelligent performance of a screening system are improved.

A method for lung monitoring provided by a lung monitoring system, includes: obtaining respiratory intensity of lung sound signals measured at a chest of a patient; generating lung sound tomographic images divided into lung regions by displaying a respiratory intensity at the lung regions corresponding to a position where the lung sound signals are measured; calculating a peak compliance according to a variation in a positive end-expiratory pressure (PEEP) value for each lung region of the lung sound tomographic image; and determining an optimal PEEP range of the patient based on a PEEP value corresponding to the peak compliance for each lung region.

This paper proposes a COVID-19 patient detection method based on capsule networks and attention mechanisms. The main steps are as follows: First, the classic U-net network structure is trained to segment lung regions in CT scans. After successful training, this network is used for lung region segmentation. Next, a slice-level feature extraction network based on capsule networks is built to extract primary feature maps from patient CT slices. Based on the extracted feature maps, an attention mechanism is used to determine the criticality of the slices, enhancing attention to critical slices and suppressing attention to non-critical information to extract more effective final feature information. After obtaining the final feature information, dimensionality-reduced feature information is obtained by combining max pooling and average pooling sampling. Finally, a neural network structure is used to determine the category of the reduced feature information. Experiments were conducted on CT images of 305 patients. The results show that, compared with some state-of-the-art methods, the proposed method has high performance, achieving an accuracy of 96.3%.

The invention discloses a pneumoconiosis early-stage refined screening method based on progressive risk sorting, and solves the technical problems that traditional screening depends on subjective judgment of experts, an existing model ignores a disease progressive rule, and local and global features cannot be effectively integrated. The method comprises the following steps: firstly, constructing a training data set containing a chest radiograph global image and six sub-lung region images according to GBZ70-2015 standards, constructing a screening network taking VisionTransform as a backbone, jointly extracting global and local features, generating sub-lung region continuous risk scores, performing differential sequencing modeling, and obtaining a sub-lung region continuous risk score; the local classification results are aggregated through a binary relaxation differentiable decision module, a diagnosis score is generated in combination with global feature intensity, a screening model is obtained through multi-task joint training, and sub-lung region anomaly classification and chest radiography level diagnosis results can be output by inputting an image to be screened. The disease progressive law is obviously modeled, the misclassification risk is reduced, the local and global diagnosis consistency is ensured, the screening accuracy and interpretability are improved, the dependence on experts is reduced, and the clinical applicability is high.

The invention provides a pig lung actual change detection method and device based on deep learning and electronic equipment. Comprising the following steps: deploying an image acquisition device at a specified station of a slaughtering assembly line, triggering to acquire original images of pig lungs, and screening out qualified normal images; inputting the normal image into a pre-trained semantic segmentation model for reasoning, recognizing a lung region in the image and a real variable region in the lung region, and generating a corresponding recognition result; and performing data statistics and analysis based on an identification result, and outputting a detection report for pig herd health assessment. Manual visual inspection is completely replaced, the efficiency of lung actual change detection on a slaughter assembly line is remarkably improved, and the system adapts to the modernized high-speed production rhythm.

The invention belongs to the technical field of image separation, and particularly discloses a lung X-ray image segmentation method with multi-level supervision. The method comprises the following steps: (1) reading an X-ray image file; (2) preprocessing the image through filtering, correction and the like; and (3) detecting a lung region in the image by using the lung region segmentation algorithm model. According to the algorithm model, U-Net is used as a main network, a multi-scale feature extraction module and an attention feature module are added in Shartcut Consection, the variety diversity of image features is increased, the background noise influence is reduced, meanwhile, a supervision mechanism is added in different branches of the U-Net, the background influence is further reduced, edge details of a lung region are effectively reserved, and accurate segmentation of the lung region is achieved. And (4) marking a lung contour area in the X-ray image, so that a doctor can carry out next detection conveniently. The method achieves the balance between the segmentation precision and the real-time performance, has very high practical value and economic value, and provides a new thought for intelligent medical treatment.

The present disclosure relates to a lung segmentation, lung disease evaluation method and device, electronic equipment and storage medium, and relates to the technical field of DR lung image segmentation. The segmentation method comprises: acquiring a segmentation model of a preset convolutional neural network, a DR lung region label image used for training the segmentation model, and a plurality of DR lung images to be segmented at multiple moments in a breathing process or a breath-holding state; wherein the method for determining the DR lung region label image used for training the segmentation model comprises: respectively performing rib edge boundary, lung apex boundary, and mediastinum and diaphragm edge detection on left chest images and right chest images of the plurality of DR lung region images to obtain the DR lung region label image; training the segmentation model by using the DR lung region label image; and completing left lung and / or right lung segmentation of the plurality of DR lung images to be segmented based on the trained segmentation model. Lung region segmentation and lung disease evaluation of DR lung images can be realized.

A system for the automated detection of lung anomalies using deep learning-based computed tomography image reconstruction, comprising: a computed tomography unit configured to generate raw projection data corresponding to a thoracic region of a subject; a preprocessing unit operationally coupled to the computed tomography acquisition unit and configured to convert the raw projection data into normalized projection representations through logarithmic transformation, scatter correction, and geometric calibration;a reconstruction processor that is communicatively linked to the preprocessing unit and configured to reconstruct volumetric image data from the normalized projection representations using a trained deep neural network architecture consisting of a multitude of convolutional layers arranged for feature extraction in projection space, domain transformation, and image space refinement; a segmentation processor that is operationally coupled to the reconstruction processor and configured to segment the reconstructed volumetric image data into lung regions and subregions based on learned spatial features; a feature extraction processor configured to derive spatial, morphological, and textual features at various scales from the segmented lung regions;a classification processor that is operationally coupled to the feature extraction processor and configured to identify and classify lung anomalies based on the extracted features using a trained neural network; and a visualization unit configured to display detected anomalies and generate diagnostic outputs, wherein the reconstruction processor and the classification processor are further configured to work together so that the classification results influence the refinement of the reconstruction.