32 results about "Nodulations" patented technology

The invention belongs to the technical field of medicine, and discloses a pulmonary nodule intraoperative positioning system based on a flexible array sensor, which comprises the flexible array sensor arranged at a to-be-detected part of a subject and used for collecting a compression signal and obtaining stress distribution; the nodule area detection unit is used for determining a nodule area through clustering analysis according to the stress distribution; the morphological optimization unit is used for performing morphological optimization on the determined nodule region; the feature extraction unit is used for extracting related geometric features based on the optimized nodule region; and the visualization unit is used for visually displaying the stress distribution, the optimized nodule region and related geometric features. The method can assist doctors in accurately positioning the pulmonary nodules, and meanwhile, quantitative features of the nodules are provided.

The present invention provides a composition for restoration of tissue including a biodegradable polymeric copolymer which is obtained by polymerizing a hydrophobic biodegradable polymer and a hydrophilic biodegradable polymer. The composition of the present invention has excellent tissue restoration effects because of high collagen production rate without occurrence of nodules even when injected directly into the dermis, unlike the conventional composition for restoration of tissue.

The present disclosure provides a method for reducing, removing, or dispersing a dermal filler aggregate in a subject. The method includes contacting a target area of the subject’s skin with a device configured to apply vibrational or mechanical energy, and applying vibrational energy to the target area for a duration sufficient to facilitate reduction, removal, or dispersion of the dermal filler aggregate. The vibrational energy may be applied while the device is held stationary over the aggregate or moved across the target area in vertical, horizontal, circular, or sweeping motions. In certain embodiments, the device is configured to contact the skin, and visible light is optionally applied during treatment. Application of vibrational energy promotes mechanical disruption and redistribution of dermal filler material within the surrounding tissue, thereby reducing the palpability or appearance of filler nodules, clumps, or irregularities.

A brush includes a body, and a plurality of nodules disposed on at least one surface of the body and at least partially protruding outward from the body. The plurality of nodules include a plurality of first nodules. Each nodule of the plurality of first nodules includes a housing including an open side and an accommodating space, and a rotating ball including a portion accommodated inside the accommodating space of the housing and a remaining portion exposed to an outside of the housing. The rotating ball is rotatable.

The present disclosure provides an image-based intraoperative positioning method for lung nodules, comprising: predicting distances between an intraoperative lung nodule and a plurality of lung feature points based on a neural network model; drawing circles with each lung feature point as the center and the predicted distance between the intraoperative lung nodule and the corresponding lung feature point as the radius, to obtain a plurality of intersection points; screening a plurality of positioning intersection points from the plurality of intersection points; and calculating the geometric center of the plurality of positioning intersection points to obtain the intraoperative position of the lung nodule. The method can automatically locate the lung nodule on the lung model after intraoperative collapse, and does not require additional devices during the operation. The present disclosure also provides an image-based intraoperative positioning device for lung nodules, equipment and media.

The invention relates to a composition intended to improve plant growth comprising at least one strain of bacteria belonging to the species Mitsuaria noduli, preferably the Mitsuaria noduli strain filed with the CNCM on July 30, 2021 under No. I-5724 or I-5725; and the use of such a strain as a biostimulant.

A method for producing biomass from a microalgae includes culturing the microalgae in an effluent diluted in seawater. A method for bioremediating an effluent includes culturing a microalgae in the effluent diluted in seawater. The microalgae is at least one of a strain of the genus Nodularia, a strain of the genus Chrysoreinhardia, a strain of the genus Halochlorella, or combinations thereof. At the beginning of culturing, the diluted effluent exhibits concentrations of total nitrogen (N) in the range of 30-150 mg / l and concentrations of total phosphorus (P) in the range of 1-15 mg / l. The N / P quotient is in the range of 5-40.

Textured polyvinyl alcohol (PVA) brush nodules and brush assemblies are disclosed for wet cleaning of sensitive substrates such as semiconductor wafers. A cylindrical brush includes a core configured for rotation and a plurality of PVA nodules disposed on the core. Each nodule has a nodule face including molded-in surface geometry (e.g., ridges and grooves) configured to disrupt and redistribute liquid at a brush / substrate interface, promote interface shear, and reduce hydroplaning-like fluid lift to help maintain contact under wet conditions. In certain embodiments, a fluid management arrangement directs cleaning liquid toward the nodule faces so that liquid exits predominantly at or through the nodule faces, improving purging and reducing water and chemistry consumption. Modular rail embodiments and manufacturing methods, including planar tray molds with CNC-machined cavity face surface geometry for forming textured nodule faces, are also described.

The present invention provides a composition for restoration of tissue including a biodegradable polymeric copolymer which is obtained by polymerizing a hydrophobic biodegradable polymer and a hydrophilic biodegradable polymer. The composition of the present invention has excellent tissue restoration effects because of high collagen production rate without occurrence of nodules even when injected directly into the dermis, unlike the conventional composition for restoration of tissue.

The application belongs to the technical field of medicine, and discloses a lung nodule intraoperative positioning system based on a flexible array sensor, which comprises a flexible array sensor, is arranged at a detection site of a subject, is used for collecting a pressure signal, and obtains a stress distribution; a nodule region detection unit, which is used for determining a nodule region through cluster analysis according to the stress distribution; a morphological optimization unit, which is used for performing morphological optimization on the determined nodule region; a feature extraction unit, which is used for extracting relevant geometric features based on the optimized nodule region; and a visualization unit, which is used for visually displaying the stress distribution, the optimized nodule region and the relevant geometric features. The application can assist doctors to realize accurate positioning of lung nodules and provide quantitative features of the nodules.

The application discloses a lung nodule medical image segmentation method based on nodule symmetry constraint, and relates to the technical field of medical image processing. The method comprises the following steps: after the CT data is preprocessed, features are extracted and a nodule center is predicted by using a deep network; based on the center, differentiable radial sampling is performed, a radial feature sequence is constructed, and boundary radii in each direction are predicted; a radius consistency loss and an opposite profile consistency loss are calculated, a symmetry mask is constructed, and the symmetry mask is fused with a basic segmentation response; finally, thresholding and center-based connected domain extraction are performed to output a final mask. By explicitly embedding a geometric morphological prior in the network, the radial symmetry of the nodule is utilized to effectively distinguish blood vessels from nodules, the problems of lacking geometric constraints, being prone to misjudgment of blood vessels and relying on complex post-processing in the prior art are solved, and end-to-end high-precision lung nodule segmentation is realized.

The invention provides a method and a system for automatically extracting ultrasonic contrast peak frames to distinguish benign and malignant nodules. An ultrasonic contrast video is analyzed based on deep learning and a time intensity curve; through an improved YOLOv5 target detection and segmentation model and in combination with a region positioning adaptive algorithm, accurate positioning and continuous tracking are carried out on nodules in the ultrasound contrast video; and time intensity curve analysis is completed by adaptively selecting a reference region, peak frames and peak time of an ultrasound contrast video are efficiently extracted and input into a deep learning classification model, and the function of predicting and classifying benign and malignant gland nodules is realized. According to the method, the consistency and comparability of clinical diagnosis are remarkably improved, the method has the advantages of being high in efficiency, high in robustness and the like, the analysis efficiency is greatly improved, and the consistency of cross-platform analysis results is improved; the method is full in process automation, high in clinical practicability, good in clinical transformation prospect and convenient for secondary development, popularization and application of scientific research institutions and medical institutions.

The invention relates to the technical field of personal health risk assessment, in particular to a pulmonary nodule operation intervention assessment system based on image analysis. The method comprises the following steps: firstly, acquiring CT images of the lung of a patient in different preoperative periods and all nodules in each CT image; all nodules are classified and pre-classified into solid nodules, ground glass nodules and suspected partial solid nodules; further classifying all suspected partial solid nodules into partial solid nodules and ground glass nodules; and finally marking the operation risk according to the classification result of the nodules. According to the method, on the basis of the texture distinguishing features and the growth rule features of different types of nodules in the CT image, the misjudgment risk of the ground glass nodules and part of solid nodules growing on a normal lung tissue structure is reduced, so that the nodules are accurately classified, and the operation intervention necessity is accurately evaluated.

The invention discloses a pulmonary nodule detection method based on a 3D dual-path residual network, and the method comprises the steps: firstly collecting lung CT images, and carrying out the preprocessing of each lung CT image, and forming training data for a subsequent 3D dual-path residual network; and then, a 3D dual-path residual network is constructed and trained to converge, and finally, through the trained 3D dual-path residual network, pulmonary nodule position and size prediction is realized for test data.

The invention discloses an intelligent pulmonary nodule image processing system and method based on a lightweight multi-scale convolutional network, and particularly relates to the field of image processing, and the system comprises a data preprocessing module, a segmentation network training module, a prediction module and a post-processing module. According to the method, HU windowing interception and normalization to [0, 1] are firstly carried out, resampling is carried out to unify voxel pitch, a segmentation network is constructed based on improved U-Net, a Ghost unit and depth separable convolution are integrated into an encoder to carry out lightweight feature extraction, and a decoder gradually recovers resolution through combination of deconvolution and residual jump connection; bCEDiceLoss joint optimization is adopted for training, and an Adam optimizer and a cosine annealing strategy are matched; in the prediction stage, overlapped sliding window block reasoning is used, and a fusion result is subjected to Gaussian weighting; post-processing is carried out, a structured report is generated through binarization, connected domain filtering and morphological closed operation, and quantitative indexes are output.

The present invention relates to a tubular dental stick along its entire length, shaped like a modified and improved conventional straw for oral hygiene use, nodulated or ringed, hollow and flexible, with a 45º angled termination at the ends to facilitate access to interdental spaces.

This invention provides a red yeast rice fermentation product for eliminating nodules. A group of important compositions for eliminating nodules were screened and obtained, including dihydroquercetin, Tian Shan snow lotus culture, chicken gizzard lining, dandelion, prunella vulgaris, platycodon grandiflorus, and black buckwheat. The culture medium was prepared using the traditional Chinese medicine composition, and red yeast rice was inoculated for fermentation. This process transformed the large active molecules in the traditional Chinese medicine composition that eliminate nodules into small active molecules such as aglycones, thereby enhancing the efficacy of eliminating nodules and significantly improving the therapeutic effect of the traditional Chinese medicine composition in eliminating nodules, thus meeting clinical needs.

The invention discloses a lung cancer CT image recognition method and device based on a heterogeneous dense network, and belongs to the field of medical image artificial intelligence. The method comprises the following steps: acquiring a lung CT image to be identified; the image is input to a pre-trained heterogeneous dense neural network for feature extraction and recognition, the heterogeneous dense neural network adopts a differentiated architecture based on connection line parity, and odd connection lines integrate multi-scale cavity convolution to capture pulmonary nodule multi-scale context features, an even number of connecting lines integrate adaptive attention convolution to enhance nodule local details and malignant sign features; and generating an identification result containing the pulmonary nodule segmentation map, the malignancy probability and the positioning information based on network output. According to the method, network architecture innovation and lung cancer image characteristics are deeply combined, so that the recognition accuracy and clinical practicability of pulmonary nodules, especially early-stage tiny nodules and difficult nodules, are remarkably improved.

The application relates to a multi-domain lung nodule detection method, device and equipment and a readable storage medium, which comprises a segmentation module, which performs axial, coronal and sagittal segmentation on a 3D feature map to obtain a plurality of slice groups in each direction; a projection sub-module, which performs nonlinear projection on each slice group to obtain a splicing adjustment value of each slice group; a domain perception sub-module, which processes each slice group to obtain a domain perception weight value of each slice group, combines the domain perception weight value and the splicing adjustment value to obtain a response vector of each slice group; a splicing and fusion sub-module, which adjusts the channel response of the slice group through the response vector to obtain a target slice group, splices the target slice groups in the same direction to obtain a target splicing map in each direction, fuses the target splicing maps in all directions based on a three-way cross attention mechanism to obtain a fusion feature map, and a detection head performs lung nodule detection and recognition on the fusion feature map, thereby improving the accuracy and robustness of multi-center lung nodule detection.

This invention discloses a medicinal and edible homologous nodule-resolving composition, belonging to the technical field of traditional Chinese medicine compositions. It is characterized by comprising the following raw material components in parts by weight: 5-15 parts of Prunella vulgaris, 20-45 parts of raw lily bulb, 5-15 parts of Perilla frutescens leaf, 5-15 parts of Perilla frutescens stem, 5-20 parts of Lycium barbarum, 10-25 parts of Chrysanthemum morifolium, 2-7 parts of ginger, and 2-20 parts of peony flower. This composition is positioned as a medicinal and edible homologous product, focusing on early, long-term, and gentle conditioning after nodule formation, aiming to stabilize nodules, reduce new nodules, and alleviate anxiety, filling a gap in modern medicine's active intervention in benign nodules. Furthermore, this composition contains peony flower stamens as its core ingredient, with clearly defined components and high safety. Simultaneously, this invention develops the potentially discarded peony flower stamen resource into a valuable resource, turning waste into treasure, which aligns with the concept of sustainable development.

The present invention relates to a composition for the nutrition or drink of a non-human animal comprising the combination of spirulina and Ascophyllum nodosum. It further relates to the use of this composition for improving the zootechnical performance of non-human animals.

The present application relates to the technical field of medical image processing, in particular to a multi-center lung CT nodule precision detection system based on federated learning. The client includes: a physical parameter estimation unit, which estimates the imaging physical parameters of the CT image based on the preset imaging physical prior knowledge base; a physical-semantic decoupling unit, which decomposes the CT image into physical invariant semantic features and device-specific physical encoding based on an invertible neural network; a nodule detection unit, which detects lung nodules based on the physical invariant semantic features. The central server includes: a global semantic anchor library, which stores typical nodule semantic feature vectors uploaded by each client; a hierarchical aggregation unit, which performs federated weighted aggregation on the semantic encoder parameters of each client, and does not perform cross-center aggregation on the physical adapter parameters. The feature incomparability problem caused by the difference of imaging devices in multi-center data is solved, and cross-center semantic alignment is realized under the premise of protecting data privacy.

1. Name of the product in this design: Fascial nodule release probe. 2. Purpose of this design: to release fascia. 3. The key design feature of this product is its shape. 4. The image or photograph that best illustrates the design's key points: a 3D model.

The invention discloses an image database establishment method for image follow-up visit of multiple cardiopulmonary nodules, and belongs to the technical field of medical data processing. The method comprises the steps of constructing a multi-center data collaborative acquisition system to generate a multi-dimensional original data set, designing a dynamic classified storage architecture based on nodule evolution characteristics, and constructing a multi-center collaborative management and security sharing platform. The internal relation among the nodule evolution rule, the clinical outcome and the biomarker level is deeply mined through a multi-dimensional dynamic association mapping mechanism, nodule state changes are automatically identified and historical data are associated when new follow-up visit data are uploaded, and a complete data chain of a target nodule can be rapidly obtained. Nodule evolution key indexes are comprehensively extracted by the dynamic association rule to construct a core feature set, comprehensiveness of nodule evolution state evaluation is ensured, definition standards of different evolution types are defined by standardized evolution state division, and a dynamic association triggering mechanism intelligently adjusts the association rule according to nodule state changes to ensure comprehensive association of key data.

The invention belongs to the technical field of plant tissue culture, and relates to a method for obtaining regenerated plants through suspension culture of peony meristematic nodules, which comprises the following steps: 1) inducing meristematic nodules; 2) suspension culture multiplication; 3) differentiation culture; and 4) plant regeneration. According to the method, clustered meristematic nodules formed by inducing peony cotyledon calluses are used as explants, the explants are cut and then transferred into a liquid culture medium for suspension culture so as to greatly increase the number of the meristematic nodules, then the proliferated meristematic nodules are transferred into a solid differentiation culture medium for bud and leaf differentiation, and then plant regeneration is achieved; the regeneration plant is obtained by establishing a peony meristematic nodule suspension culture system, and the regeneration efficiency of the peony in-vitro plant is greatly improved.

The invention provides a nodule detection model training method, a nodule detection method and electronic equipment, and relates to the technical field of model training. The method comprises the steps of firstly obtaining a first training data set and a trained first teacher model and second teacher model; wherein the first teacher model is a high-sensitivity teacher model, and the second teacher model is a high-specificity teacher model; based on the first training data set, utilizing the first teacher model and the second teacher model to train a student model through knowledge distillation; in the training process, dynamically selecting a reference model from the first teacher model and the second teacher model, and determining the distillation loss based on the output of the reference model and the student model; and finally, constructing a loss function according to the distillation loss and the basic detection loss of the student model, and performing back propagation according to the loss function to update the parameters of the student model until the model converges so as to obtain a nodule detection model. The scheme of the invention has the advantages of high recall and low false detection.

The application discloses a liposome curcumin composition for assisting in regulating nodular diseases and application thereof, and belongs to the technical field of health foods. The composition is composed of 60-80 nm liposome curcumin, 3-10 g / portion of inulin, 10-80 mg / portion of cardamom extract, 100-1000 mg / portion of myo-inositol and 20-100 mu g / portion of selenium element. The liposome is prepared by using food-grade phospholipid, the encapsulation efficiency is greater than or equal to 80%, the ethanol residue is less than or equal to 0.5 ‰, the release rate in a pH 2.0 simulated gastric juice for 2 hours is less than 33%, and the release rate in a pH 7.4 simulated intestinal juice for 4 hours is greater than 80%. The application is based on the theory of treating different diseases in the same way, and four types of nodular core pathogenesis, such as inflammatory accumulation, endocrine disorder, oxidative stress and immune imbalance, are simultaneously intervened by the synergistic effect of multiple components, so that the synchronous auxiliary regulation of thyroid, breast and uterus multiple types of nodules is realized. The product fills the blank of lack of effective intervention means in the clinical regular observation period, and is suitable for the daily regulation of patients with various nodular diseases and the use for preventing recurrence after operation.