16 results about "Color flow" patented technology

The invention discloses a multi-modal ultrasonic image intelligent analysis system based on deep learning, particularly relates to the field of ultrasonic image intelligent analysis, and is used for solving the problems of speckle noise and displacement artifacts caused by sound beam attenuation during deep abdomen scanning of a bedside ultrasonic person with a relatively high in-vivo quality index. Partition noise reduction is guided through pixel noise distribution associated with depth and attenuation, and deep micro-textures are reserved; the color flow velocity and the elastic displacement are anchored through the noise reduction gray scale edge, three-mode sub-pixel alignment is completed, and cross-channel deformation and drift are eliminated; the self-attention fusion network synchronously extracts texture, speed and hardness features on the unified alignment surface to realize coupling of a complete biological structure and dynamic information; the texture residual error rate and the flow rate matching degree form complementary evaluation, noise distribution and alignment grid real-time self-adjustment are driven, frame-by-frame iteration convergence is achieved, and image definition and feature consistency are continuously improved.

The invention relates to an acute leukemia (ALL) high-throughput flow cytometry kit, and belongs to the field of leukemia detection.16 ALL cell antigens are added on the basis of an original 8-color flow cytometry, 24 antigens in the same cell can be detected at the same time, the detection precision of minimal residual focus (MRD) is greatly improved, and the detection sensitivity is improved. The ALL cells are divided into 12 developmental stages, so that immunological typing during primary diagnosis and immunophenotype variation after bone marrow transplantation and CAR-T cell treatment can be more accurately recognized, and the method has very important guiding significance on evaluation of treatment effects of patients and adjustment of treatment schemes.

The utility model relates to a needle valve nozzle for precise color mixing injection molding, and belongs to the technical field of injection molding hot runners. Comprising an outer nozzle head and an inner nozzle head, the inner nozzle head is fixedly arranged at the inner center of the outer nozzle head, a glue inlet is formed in the bottom of the outer nozzle head, a vertical first color runner is arranged at a shaft core of the inner nozzle head, the bottom of the first color runner is connected with the glue inlet, a second color runner is arranged in the outer nozzle head, and an annular groove is formed in the outer side wall of the inner nozzle head. The second color runner is connected with the annular groove, the inner nozzle head is provided with a plurality of vertical strip-shaped grooves, the strip-shaped grooves are uniformly distributed on the outer side wall of the inner nozzle head, the top ends of the strip-shaped grooves are connected with the annular groove, and the bottom ends of the strip-shaped grooves are connected with the glue inlet; according to the scheme, the internal structure of the nozzle head is optimized, the second-color melt can pass through the strip-shaped grooves in all directions, the first-color melt is wrapped on the inner side during mixing, and the melts of the two colors are mixed more sufficiently.

Various methods and systems for color flow ultrasound imaging of arteries and veins are provided. In one embodiment, a method comprises acquiring a color flow image, automatically identifying an artery and a vein within the color flow image, and adjusting at least one imaging parameter responsive to the automatic identification of the artery and the vein. In this way, flow velocities and volume flow in arteries and veins may be measured with minimal adjustments or input by a user, thereby increasing the accuracy and consistency of measurements and reducing the time needed for blood flow measurements.

The application provides a traffic indication method based on multispectral pedestrian detection and vehicle speed detection, obtains the number of waiting pedestrians and the number of crossing pedestrians of a target intersection through pedestrian detection based on YOLOv4; combines the number of waiting pedestrians and the number of crossing pedestrians with road information of a road section associated with the target intersection to calculate and obtain the switching time of the signal light of the target intersection; combines the number of waiting pedestrians and the number of crossing pedestrians with road information of a road section associated with the target intersection to obtain a driving speed threshold of the associated road section; detects the driving speed of the road section associated with the target intersection, and when the driving speed is not within the driving speed threshold, a warning signal is sent out at the target intersection; the pedestrian detection based on YOLOv4 includes fusing color flow and temperature flow, generating fused flow to extract features, and transmitting information of the fused flow from the bottom to the top of the neural network at different stages; and further includes fusing color flow and temperature flow according to the lighting conditions of the target intersection.

To prevent or reduce the blurring of the edge of a blood flow in the display of flow velocity data.SOLUTION: The processor removes noise from the power data 110 extracted from the color flow data 100 (block 14), and obtains a gradient at each pixel as the blood flow form information 114 from the power data 112 after noise removal (block 16). Further, the processor performs noise removal on the flow velocity data 120 extracted from the color flow data 100 using the blood flow form information 114 (block 20). In this denoising, the processor uses, for example, a denoising filter that considers, for each pixel, only a pixel group along a direction perpendicular to the gradient at the pixel.SELECTED DRAWING: Figure 2

Blurring of blood flow flanks when displaying flow velocity data can be prevented or reduced. A processor removes noise from power data extracted from color flow data and obtains a gradient at each pixel as blood flow morphology information from the power data after noise removal. Additionally, the processor performs noise removal on flow velocity data extracted from the color flow data using the blood flow morphology information. For example, in noise removal, the processor uses a noise removal filter for each pixel that considers only a group of pixels along a direction perpendicular to the gradient at each pixel.

The invention provides a single-tube multi-allergen specific basophilic granulocyte detection method based on multicolor flow cytometry, and belongs to the technical field of immunodetection. Through a single-tube multicolor flow cytometry technology, rapid and synchronous quantitative analysis of various allergen-specific basophilic granulocytes in peripheral whole blood is realized, and the detection efficiency and flux are remarkably improved; the method is easy and convenient to operate, small in needed sample size and especially suitable for children and other people with blood sampling difficulty, and the limitation of clinical application is greatly reduced; by directly measuring cell populations closely related to anaphylaxis, a more intuitive and reliable auxiliary diagnosis basis is provided for IgE-mediated anaphylaxis diseases, the immune state change of a patient in the treatment process can be effectively monitored, and a new technical support is provided for clinical precise intervention and curative effect evaluation.

A color changing indicator for detecting damage to a catheter balloon is disclosed. An assembly can comprise a delivery apparatus for implanting an implantable medical device, where the delivery apparatus can comprise a shaft and an inflatable balloon coupled to the shaft. The balloon is adapted to receive thereon the implantable medical device in a crimped state. A fluid for introducing into the balloon can be adapted to change a color of a portion of the implantable medical device and / or a portion of the delivery apparatus upon contact with the fluid when the fluid leaks from the balloon. The fluid can be adapted to change a color of the fluid upon contact with air outside the balloon.

The invention provides an ultrasound image processing apparatus, a computer program product, and a recording medium. The present invention addresses the problem of preventing or reducing blurring of a blood flow edge in display of flow rate data. A processor removes noise from power data (110) extracted from color stream data (100) (functional module (14)), and finds a gradient in each pixel from the power data (112) after noise removal as blood flow pattern information (114) (functional module (16)). And, the processor uses the blood flow morphology information (114) to noise remove flow rate data (120) extracted from the color flow data (100) (functional module (20)). In the noise removal, the processor uses, for example, a noise removal filter that takes into account only a group of pixels along a direction perpendicular to a gradient in the pixel for each pixel.

The present application relates to a kind of acute leukemia (ALL) high flux flow detection kit, belong to leukemia detection field, the present application is based on the original 8 color flow to increase 16 kinds of ALL cell antigen, can realize the simultaneous detection of 24 kinds of antigens in the same cell, not only greatly improve the detection precision of micro residual lesion (MRD), and by being divided into 12 development stages to ALL cell, can more accurately identify immunotyping when first diagnosis, and immunophenotypic aberration after bone marrow transplantation and after CAR-T cell therapy, this has very important guiding significance to the evaluation of patient treatment effect and the adjustment of treatment scheme.

The invention provides a method and a device for classifying a color blood flow map of a four-cavity heart tangent surface at an early stage of pregnancy. The method comprises the following steps: acquiring a to-be-classified color blood flow map of the four-cavity heart tangent surface; inputting a to-be-classified four-cavity heart tangent color blood flow graph into the trained classification model to obtain a classification result of the to-be-classified four-cavity heart tangent color blood flow graph; the classification model comprises an image preprocessing layer, a structure-guided image feature extraction layer, a blood flow mode feature learning layer, a blood flow mode-based dichotomy layer, an attention layer and a blood flow mode-based classifier. The accuracy and reliability of the classification result can be improved.

A processor removes noise from power data extracted from color flow data, and obtains a gradient at each pixel as blood flow morphology information from the power data after the noise is removed. In addition, the processor performs noise removal on flow velocity data extracted from the color flow data using the blood flow morphology information. In the noise removal, the processor uses, for example, for each pixel, a noise removal filter that considers only a pixel group along a direction perpendicular to the gradient at each pixel.

In one embodiment, a method of building an optimized color flow cytometry panel is disclosed using a full spectrum flow cytometer with five excitation lasers and five corresponding detection modules. In another embodiment, a graphical user interface is disclosed generated by a server computer from a fluorochrome database and displayed by a client computer to assist in the selection of a set of fluorochromes for use in an assay to analyze biological samples. The GUI can display spectra graphs to visually show how fluorochromes may overlap and can generate similarity indexes for the paired fluorochrome interference and a complexity index for overall many to many interferences generated by a selected group or set of fluorochromes.

This utility model discloses a button cover molding die, including a moving die, a first-color fixed die, and a second-color fixed die. The moving die includes a moving template, a moving core, a moving die fixing plate, and a moving die ejection mechanism. The first-color fixed die includes a first-color fixed template, a first-color fixed core, a first-color fixed die top plate, and a first-color fixed die fixing plate. The second-color fixed die includes a second-color fixed template, a second-color fixed core, a second-color fixed die top plate, and a second-color fixed die fixing plate. The moving core has two annular grooves, and at least one side of each annular groove has a moving die ejector groove. A first-color flow channel connects the two annular grooves. The second-color fixed die includes two recessed annular grooves connected by a lateral flow channel. A protruding annular retaining ring is provided within each recessed annular groove. This utility model can achieve separate molding of the transparent layer and the aperture layer, resulting in high molding quality and ensuring the product's appearance integrity and light transmittance.

The invention discloses a ceramic color design system based on data visualization and an application method thereof, and the method comprises the following steps: preprocessing ceramic image data through a computer vision technology, and constructing a ceramic-color bipartite graph network connecting a ceramic work and a color as a basic model; the bipartite graph network is projected into a weighted color co-occurrence network and is used for revealing and quantifying a matching rule between colors; a user can dynamically adjust a CIEDE2000 color difference threshold through a visual interaction interface to simplify the co-occurrence network, and center analysis is combined, so that a core design color plate is extracted from a network topology structure; the method also supports generation of visual display plates such as an age-color-classification-color system-style five-level color flow mulberry-based graph so as to assist in analysis of macroscopic association of colors and cultural attributes. The invention is mainly used for providing a data-driven innovative tool capable of systematically mining traditional color matching genes for modern design.