81 results about "Urinary sediment" patented technology

The invention provides an automatic identification system for urinary sediment visible components based on a support vector machine, which comprises an image acquisition module, an image data base, a primary labeling module, an image processing module, a secondary labeling module, a support vector machine forming module, a urinary sediment visible component identification module and the like, and organically combines three major procedures of image segmentation and processing, support vector machine training and urinary sediment visible component identification together to form a systemic and complete technical frame for the training and the automatic identification of the urinary sediment visible components based on the SVM method. The system can be used in the segmentation, training and automatic identification processes of the urinary sediment visible components in the view field of a microscope, and provides a basic solution for the implementation of a computer-aided detection system for routine urine examination based on a microscope.

Methods of treating lupus, including systemic lupus erythematosus, cutaneous lupus erythmetosus, and lupus nephritis, are provided. The methods involve administration of a combination of a non-depleting CD4 antibody and another compound used clinically or experimentally to treat lupus. Methods of treating lupus nephritis by administration of a non-depleting CD4 antibody that results in an improvement in renal function and/or a reduction in proteinuria or active urinary sediment are also provided. Methods of treating multiple sclerosis by administration of a non-depleting CD4 antibody, optionally in combination with another compound used clinically or experimentally to treat MS, are described. Methods of treating transplant recipients and subjects with rheumatoid arthritis, asthma, psoriasis, Crohn's disease, ulcerative colitis, and Sjogren's syndrome are also provided.

The invention discloses a non-invasive detection method and a kit for early screening a bladder cancer by multi-gene combination. The combined genes include APC, NID2 and p16, and specific methylationprimers are designed to detect three nucleotide sequences of target gene fragment methylation of the APC, the NID2 and the p16, so that early screening and auxiliary diagnosis of the bladder cancer are achieved. Methylation levels of three genetic markers of the APC, the NID2 and the p16 in urinary sediments are analyzed by a three-channel fluorescent quantitative PCR (polymerase chain reaction)method, and a positive or negative result of a sample is judged according to a reported CT (computed tomography) value. The non-invasive detection method can detect 90% of early bladder cancers, 64% of precancerous adenomas (larger than or equal to 1 centimeter) in preclinical study, specificity reaches 100%, invasiveness is completely omitted, the method only needs to collect urine of 50mL, and acceptability of throngs wearing no symptoms is high.

The invention discloses a method for automatically identifying urinary sediment visible components based on Trimmed SSD. The method comprises steps that firstly, local detail features and global semantic features are extracted by the feature extraction network composed of the basic convolutional network and the auxiliary convolutional network; secondly, three feature maps are selected by the target identification network as input from different layers of the feature extraction network, after three sets of convolutional filtering, the confidence and rectangular frame coordinates of all the categories are obtained, and lastly, through a prediction result screening module, a few rectangular frames with the relatively high confidence are filtered out to get the final prediction result. The method is advantaged in that the Trimmed SSD full convolutional identification network is constructed, the precise regional segmentation phase and the manual feature extraction process are avoided, for urinary sediment visible component identification tasks, feature extraction, classification and positioning learning are autonomously carried out in an end-to-end monitoring mode.

The invention relates to the field of medical image processing, in particular to a urine visible component recognition method based on an improved Alexnet model. The method comprises the following steps: 1, acquiring and expanding an image data set, and constructing a urinary sediment image training set and a test set; 2, constructing a urine visible component recognition network model based on anAlexnet network model; 3, setting training parameters of the urine visible component recognition network model; 4, training a urine visible component recognition network model based on an Alexnet network model; 5, testing a urine visible component recognition network model based on the Alexnet network model. The method is improved on the basis of an Alexnet network model and reduces the number ofnetwork training parameters. The method can automatically extract image features, has the characteristics of high recognition rate, short recognition time and strong generalization ability, and has important application prospects for assisting medical diagnosis and reducing the burden of doctors.

The invention discloses a two-channel liquid path system of a urinary sediment analyzer, which comprises a sampling needle, a liquid guide pipe, a connecting pipe, three three-way electromagnetic valves, a channel A, a channel B, three liquid pumps and a flow pool, wherein the sampling needle is divided into two sampling channels which are respectively the channel A and the channel B after connected with a three-way electromagnetic valve by the liquid guide pipe; the channel A and the channel B are combined by another three-way electromagnetic valve and connected with the liquid pumps by the liquid guide pipe; the channel A comprises a connecting pipe, two three-way electromagnetic valves and a liquid storage pipe; the two three-way electromagnetic valves are connected in series; the two three-way electromagnetic valves are connected by the liquid storage pipe; the channel B comprises a connecting pipe, two three-way electromagnetic valves and a liquid storage pipe; the two three-way electromagnetic valves are connected in series; and the two three-way electromagnetic valves are connected by the liquid storage pipe. The invention has the advantages of greatly improving the test speed of the urinary sediment analyzer and realizing the parallel processing of two sample sucking channels in a test channel.

Methods of treating lupus, including systemic lupus erythematosus, cutaneous lupus erythmetosus, and lupus nephritis, are provided. The methods involve administration of a combination of a non-depleting CD4 antibody and another compound used clinically or experimentally to treat lupus. Methods of treating lupus nephritis by administration of a non-depleting CD4 antibody that results in an improvement in renal function and/or a reduction in proteinuria or active urinary sediment are also provided. Methods of treating multiple sclerosis by administration of a non-depleting CD4 antibody, optionally in combination with another compound used clinically or experimentally to treat MS, are described. Methods of treating transplant recipients and subjects with rheumatoid arthritis, asthma, psoriasis, Crohn's disease, ulcerative colitis, and Sjogren's syndrome are also provided.

The invention discloses an integrated nephrology urinary sediment microscopy device which mainly comprises a base body, a high-speed centrifugal device, a liquid taking telescopic device and a microscopy device body. The high-speed centrifugal device is embedded into the base body, the liquid taking telescopic device is connected on the upper portion of the base body through a vertical column and a horizontal supporting plate, the microscopy device body is connected on the upper portion of the horizontal supporting plate through a vertical supporting plate, a first liquid guide protection sleeve and a second liquid guide protection sleeve are longitudinally, bilaterally and parallelly arranged in the inner middle of the liquid taking telescopic device and sleeve a liquid supernatant guide pipe and a urinary sediment guide pipe in a penetrated manner, one end of the liquid supernatant guide pipe is connected with a waste liquid bottle, and the upper end of the urinary sediment guide pipe is communicated with a double-layer slide in the microscopy device body. The device is reasonable in design and convenient to operate, and working efficiency can be greatly improved.

The invention discloses a double-lens-cone microscope device used in urinary sediment inspection equipment. The double-lens-cone microscope device comprises a supporting block, a high power objective, a low power objective, a counting cell, a light source, two objective connecting cylinders and two CCD sensors, wherein the two objective connecting cylinders are installed on the supporting block, and the two CCD sensors are installed above the objective connecting cylinders respectively. Three diaphragms are arranged inside each objective connecting cylinder at intervals. The light source is placed at the position far away from the counting cell, the light source comprises two LED light source bodies and two optical fibers, one end of each optical fiber is located below the counting cell and directly faces the counting cell, and the other end of each optical fiber directly faces the corresponding LED light source body. The parts form a high power microscope system and a low power microscope system respectively, and the central axes of the CCD sensor, the objective connecting cylinder, the high power objective or the low power objective and the light source optical fiber which all belong to the same set of microscope system coincide. The double-lens-cone microscope device is simple in structure, can shoot visible components in urine under different powers at the same time, saves shooting time and improves inspection speed.

The invention discloses a dry chemical detection system of a full-automatic urine detector. The dry chemical detection system comprises a urine storage system and a urinary sediment detection system, wherein the urine storage system is used for conveying urine in a specific urine storage pipe into a urine immersion pipe through a quantitative pump device, and a test paper strip is immersed in the urine; after the test paper strip is immersed in the urine for set urine immersion time, a manipulator device in the urinary sediment detection system lifts up the test paper strip and conveys the test paper strip to be in front of a dry chemical detection camera device for shooting; then the urine is treated by a treatment device of a urinary sediment analyzer, and the manipulator puts the test paper strip into a waste barrel.

The invention relates to a method for identifying transparent tube type, pathological tube type and mucus silk in urinary sediment, which comprises the following steps: 1, collecting segmented urine visible component microscopic pictures, and randomly dividing the pictures into a training set and a test set in proportion; 2, preprocessing the training set data; step 3, constructing a urine-8Net urine visible component identification network; 4, setting used network parameters; 5, training a urine-8Net urine visible component recognition model based on the urine8Net urine visible component recognition model in the step 3; and step 6, testing the obtained model by using the urinary sediment image test sets obtained in the step 1 and the step 2 to obtain an identification result and overall accuracy of the tubular components in the test set. According to the invention, image features can be automatically extracted, effective fine-grained recognition is carried out on selected urine visible components, the invention has the characteristics of high accuracy and high recognition speed, and the invention has a wide application prospect in clinical urinary sediment recognition and inspection.

The invention discloses an automatic urinary sediment rinsing machine with a negative pressure decompression protection function. The machine comprises an automatic rinsing component and an automaticflow guide component. The automatic rinsing component comprises a solution bottle or a solution bag which is filled with rinsing fluid and a peristaltic pump which provides power, and the peristalticpump and the solution bottle or the solution bag are connected through a rinsing pipe component; the automatic flow guide component comprises a fluid collection device which is used for containing waste fluid and a flow guide pipe component which is matched with the fluid collection device; the rinsing pipe component and the flow guide pipe component are communicated with a urinary catheterizationcomponent through a tee coupling. A negative pressure decompression valve which conducts decompression protection on negative pressure in the fluid collection device is arranged on the negative pressure pump. According to the automatic urinary sediment rinsing machine with the negative pressure decompression protection function, the whole ringing process is automatically conducted by the machine,manual operation is not needed, the pouring pressure of the rinsing fluid is constant, and the clinical working intensity is low; a catheter is not needed to be subjected to any operation in the whole rinsing process, a urethral catheter cannot be shifted, and the rinsing fluid or waste fluid cannot overflow in the rinsing process.

The invention relates to the field of medical image processing, in particular to a urinary sediment image recognition system and a urinary sediment image recognition method based on deep learning. Animage acquisition module acquires the urine sample to obtain an original image. An image segmentation module performs segmentation processing on the original image to obtain a segmented urinary sediment component image. An image recognition module based on deep learning is used for recognizing the segmented urinary sediment component images and integrating recognition results of the three networkmodels to obtain output of the image recognition module based on deep learning. A counting module performs statistical processing on the output result to obtain a quantitative medical index reference.The system outputs the result of the image recognition module and the result of the counting module based on deep learning. According to the method, end-to-end feature extraction and classification can be automatically realized, and tiny features, which are difficult to find by naked eyes, in visible components of the urinary sediment are effectively extracted, so that the problem of complex classification of 11 urinary sediment components is solved with high quality, and the method has very high medical application value.

The invention discloses a sheath fluid used for urinary sediment analysis and a preparation method thereof. The sheath fluid comprises mother liquor as well as sodium chloride and glycerol substances which are dissolved in the mother liquor, wherein a buffering agent, a surfactant and a chelating agent are dissolved in the mother liquor, pH value of the mother liquor is 7-8; the mother liquor also contains a mould inhibitor and an antibacterial agent; the glycerol substances comprise glycerol and polyglycerol, wherein working concentration of the glycerol is 50-60g/L preferably; and the surfactant is a polyoxyethylene ether type surfactant and sorbitol polyoxyethylene ether preferably, and the working concentration of the surfactant is 100-2000mg/L and 300mg/L preferably. The sheath fluid disclosed by the invention is relatively stable in properties, and precipitates can be difficultly produced; the sheath fluid is applicable to an import instrument, and using effect of a domestic instrument is also considered, so that application range is wide and price is relatively lower; and corrosion to a metal part of the instrument is less, so that usage cost is greatly reduced.

The invention relates to the field of cell pathology detection, in particular to a method of extraction and flaking of body fluid cells for checking bladder cancer. The extraction method comprises a sampling process and a treatment process. According to the method of extraction of body fluid cells for checking bladder cancer, urine sediment is broken and decomposed without damage, the problems that urine cells cannot be stored for a long time and the quantity of the cells is small due to the fact that the urine is autolyzed after leaving the human body for 2 hours are solved, the urine samplecan be stored for 7-10 days, the problem that the inspection turnover time is not enough is thoroughly solved, and the non-invasive detection can really benefit the public. The first morning urine with the most abundant diagnostic information and the most urinary sediments is adopted so that exfoliated cells can be completely dissociated from the urinary sediments, more than 5000 cells can be collected from the first morning urine and the sampling quantity, quality and detection success rate are greatly improved.

The invention provides a method for detecting the heterogeneity of mitochondrial genome A3243G site. The method comprises the following steps: (a) preparing a standard substance containing wild type and mutant type plasmids in a mitochondrial genome A3243G site fragment; (b) directly taking non-nucleic acid templates as templates to be detected, using a real-time quantification polymerase chain reaction (PCR) technology to carry out single nucleotide polymorphism (SNP) analytic detection on the A3243G site, and using a minor groove conjugate probe (MGB) probe for marking. According to the method, a conventional operation step of extracting nucleic acid DNAs as templates by using PCR is changed, the non-nucleic acid templates such as white cells, urinary sediment, saliva sediment and hair follicles are directly taken as templates, and a preferable result is obtained, so that the detection time is simplified.

Methods of treating lupus, including systemic lupus erythematosus, cutaneous lupus erythmetosus, and lupus nephritis, are provided. The methods involve administration of a combination of a non-depleting CD4 antibody and another compound used clinically or experimentally to treat lupus. Methods of treating lupus nephritis by administration of a non-depleting CD4 antibody that results in an improvement in renal function and/or a reduction in proteinuria or active urinary sediment are also provided. Methods of treating lupus or decreasing autoantibody titer by administration of a non-depleting CD4 antibody are also provided. Methods of treating multiple sclerosis by administration of a non-depleting CD4 antibody, optionally in combination with another compound used clinically or experimentally to treat MS, are described. Methods of treating transplant recipients and subjects with rheumatoid arthritis, asthma, psoriasis, Crohn's disease, ulcerative colitis, and Sjogren's syndrome are also provided.

The invention discloses a sectional non-linear enhancement method for a urinary sediment image. The method comprises the following steps of: a first step: calculating section points by using a genetic algorithm according to distribution ranges of cells in the image and background in a gray space, dividing the whole image into a background section, a target section and a transition section according to the section points, calling a gray-level zone of distributed background as the background section, counting the gray-level zone of each distributed cell, ensuring that the gray-level zones in which the backgrounds and the cells are distributed have overlapped and crossed areas to find out the most proper thresholds to divide the two zones, and selecting a gray-level zone with less than 100 pixels as the transitional section; and a second step: performing different gray-level transformation method on the background section, the target section and the transition section. The method has the beneficial effects that the enhancement method is high in processing speed and stable and reliable; and the noise of the background is well inhibited, and the whole image is obvious in vision effect.

The invention provides a urinary sediment microscopic image visible component recognition method based on deep learning. The method comprises the steps that an AlexNet model is improved to be De-; Themethod comprises the following steps: establishing a visual convolutional neural network model, establishing an AlexNet model, migrating model parameters, utilizing the visual convolutional neural network model to formulate a reasonable fine tuning learning rate and cascading feature strategy, and integrating De-; The AlexNet model, the GoogLeNet model and the ResNet model carry out feature extraction on the urinary sediment microscopic image, and a full-connection neural network model is designed as a classifier to classify the integrated features. Compared with an existing urinary sedimentmicroscopic image visible component recognition method, the urinary sediment microscopic image visible component recognition method is higher in recognition accuracy, simpler in operation and better in efficiency.

The invention discloses a deep learning-based urine visible component detection method and device. A single-stage target detection algorithm with higher detection speed is used, and a network model with fewer parameters is used; a local context attention module and a global background suppression module are provided for the global sparse and local dense characteristics of the urinary sediment image to improve the detection effect, so that the model pays attention to a region containing a target; the distinguishing capability of targets in a dense area is enhanced, and attention to the background is reduced. According to the technical scheme, for the urinary sediment picture, urine visible components in the picture can be effectively detected, and the situation of local dense distribution detection is greatly improved.

The invention provides a digital microscope for urinary sediment detection and an image identification method using the digital microscope. The digital microscope comprises an optical microscopic device used for imaging a to-be-detected sample into an amplified image; an imaging device, used for collecting images imaged by the optical microscopic device; a displayer, used for displaying the images collected by the imaging device; and a control device, used to control the imaging device and the displayer and receive image data collected by the imaging device and send the image data to the displayer; wherein the imaging device is provided with an imaging chip, the imaging chip size is 1 / 4 inch-1 inch, and the frame rate is greater than 25 frames per second. The digital microscope is good in imaging effect, accurate in component identification, and low in cost, and can satisfy the wide remote area medical need.

A specimen inspection system 10 includes a urinary sediment device 30 and an information processing device 50. The information processing device 50 includes a control part 51, a display part 53, and an input part 54. The control part 51 causes the display part 53 to display a screen 100 including a reference information display area 120 for displaying an analysis result of a specimen received from the urinary sediment device 30 and an input value display area 110 to be used in a visual inspection of the specimen using a microscope 60. The control part 51 receives a value of physical components counted in a visual inspection of the specimen through the input part 54 while the screen 100 is being displayed, and displays the received count value in the input value display area 110.