45 results about "Cell smear" patented technology

The invention provides a blood cell detection method and system based on a microscopic multispectral image, and relates to the field of blood cell detection.The blood cell detection method based on the microscopic multispectral image comprises the following steps that S01, pre-scanning is carried out, performing low-resolution pre-scanning on a sample area of the input cell smear, and screening a plurality of candidate view fields based on a preset view field selection algorithm; s02, performing multi-direction scanning according to the spatial distribution of the candidate visual fields. Through the cooperation of the above structures, the system has the following beneficial effects: 1, multiple sampling can be carried out, the optimal view can be selected, and the recognition efficiency can be improved; secondly, a plurality of single-spectrum band images can be synthesized into a full-light image, and compared with a traditional single-wavelength image, more cell characteristics and details can be provided; and thirdly, the focal length can be dynamically adjusted, and accurate focusing on a plurality of specific layers is realized.

The invention relates to the technical field of clinical detection of cerebrospinal fluid, and particularly discloses a smear device for detecting cerebrospinal fluid, which mainly comprises a sample tube and a piston assembly, the sample tube comprises a first tube body, a second tube body and a third tube body; the second pipe body is located above the first pipe body, a liquid outlet hole is formed in the bottom, and a liquid inlet hole is formed in the side wall; the bottom of the third pipe body is communicated with the liquid inlet hole through a flow channel; the piston assembly comprises a piston, a handle part and a center rod; the piston is fixedly connected with a tongue part, the center rod can be inserted into the liquid outlet hole, and the piston assembly is provided with an initial station and a flaking station. According to the smear device for detecting the cerebrospinal fluid, the manufacturing process of a cell smear is simplified, operation is convenient and fast, the smear manufacturing efficiency is remarkably improved, the smear manufacturing time is shortened, unnecessary physical damage to cells in the smear manufacturing process is avoided, then cell rupture and dissolution can be effectively reduced, and the smear quality is remarkably improved; meanwhile, the comprehensive cost of manufacturing the cell smear is obviously reduced.

The invention discloses a pathological image classification method and system for assisting pathological diagnosis, and aims to solve the problems that the traditional pathological diagnosis is low in efficiency and the accuracy depends on artificial experience. According to the method, a pathological image is collected, denoising, enhancement and other preprocessing operations are executed, a pre-trained deep learning model is utilized to automatically extract image features, and classification results of benign, malignant or specific disease types are output in combination with a classification algorithm, so that efficient and accurate automatic diagnosis is realized; the system integrates image acquisition, preprocessing, feature classification and result display modules, supports multi-user concurrent access and cloud deployment, is equipped with model updating and user interaction functions, and can continuously optimize model performance based on new data. In addition, remote pathological diagnosis is supported, and balanced distribution of medical resources is promoted through a digital system; the method can significantly reduce the workload of pathologists, reduces the risk of human misdiagnosis, and is suitable for rapid classification and diagnosis of various pathological images such as tissue slices, cell smears and the like.

The present invention relates to a computer-implemented method for producing a trained model for detecting one or more defined cell types and / or cellular indicators, such as biomarkers or cellular abnormalities, in particular genomic aberrations, from single-cell images obtained from a sample of a body liquid, bone marrow, cytology smear or slide preparations, in particular a blood smear sample. It relates also to a computer-implemented method for detecting one or more defined cell types and / or cellular indicators, such as biomarkers or cellular abnormalities, in particular genomic aberrations, from single-cell images obtained from a sample of a body liquid, bone marrow or cytology smear, in particular a blood smear sample.

The utility model relates to the technical field of pathological cell smears, in particular to an automatic feeding and discharging centrifugal device, which is characterized in that a centrifugal device and a conveying device are built on a workbench on the basis of the arrangement of a rack and the workbench, the conveying device grabs a carrier of cell sap, the cell sap is sequentially put into the centrifugal device, and the centrifugal device and the conveying device are arranged on the workbench. The centrifugal operation is performed through the operation of the centrifugal device, and after the centrifugal operation is completed, the conveying device grabs the carrier of the cell sap again and takes the cell sap out of the centrifugal device in sequence, so that the automatic centrifugal operation is realized, and the production efficiency is improved.

The utility model discloses a blood cell smear auxiliary device. The blood cell smear auxiliary device comprises a blood filling pool and an adjusting part, the blood filling pool is provided with a containing groove used for containing blood, the groove bottom face of the containing groove is opened to be used for being matched with a glass slide, and the adjusting part comprises a first adjusting piece and a second adjusting piece. The first adjusting piece and the second adjusting piece are oppositely arranged in the blood filling pool, and the first adjusting piece and the second adjusting piece can move so as to adjust the volume of the containing groove. According to the blood cell smear auxiliary device, the preparation efficiency and quality of the blood smear can be remarkably improved, and a more reliable sample is provided for hematological examination, so that the accuracy and efficiency of medical diagnosis are promoted.

The utility model relates to the technical field of smear dyeing fixing devices, in particular to a blood cell smear dyeing fixing device, which solves the problems mentioned in the background technology and comprises a placing plate, a placing groove is arranged at the top of the placing plate, one end of the placing groove is flush with one end of the placing plate, and the other end of the placing plate is provided with a fixing device. One end of the placing plate is fixedly connected with a first fixing ring, the other end of the placing plate is fixedly connected with two second fixing rings, the top, close to the first fixing ring, of the placing plate is fixedly connected with a baffle, sliding grooves are formed in the two sides of the placing plate, and the same moving assembly is installed on the two sliding grooves. One end of the placing groove is flush with one end of the placing plate, so that the glass slide can be conveniently placed in the placing groove, one end of the placing plate is fixedly connected with a first fixing ring, the other end of the placing plate is fixedly connected with two second fixing rings, fingers are placed in the first fixing ring and the second fixing rings to fix the placing plate, the glass slide can be prevented from falling off, and the operation stability is improved.

The invention belongs to the technical field of cell smears, and discloses a cell filtering, sorting and enriching smear device which comprises an accommodating and resuspending mechanism, a filtering mechanism and a smear mechanism. The accommodating and resuspending mechanism comprises a sample accommodating assembly and a resuspending assembly, the sample accommodating assembly and the resuspending assembly can be coaxially and integrally connected or mutually independent, the sample accommodating assembly accommodates a liquid biological sample, and the resuspending assembly accommodates resuspending liquid; the filtering mechanism is detachably connected to the sample containing assembly and further detachably connected to the resuspension assembly, a filtering membrane is arranged in the filtering mechanism, and a liquid biological sample is filtered and enriched through the filtering membrane and then is resuspended to obtain a cell suspension; the smear mechanism is connected to the centrifugal smear machine and can bear a glass slide and contain the filtering mechanism, and the cell suspension can flow to the glass slide from the filtering mechanism. The cell filtering, sorting, enriching and smearing device can realize cell separation, enrichment and smearing processes, prevent cell loss, improve the smearing quality and shorten the smearing time.

The invention discloses a cerebrospinal fluid cell marking method and device, computer equipment and a storage medium, and relates to the technical field of cerebrospinal fluid cell marking, the cerebrospinal fluid cell marking method comprises the following steps: acquiring a cerebrospinal fluid cell image, and performing full-sheet display on the cerebrospinal fluid cell image, the cerebrospinal fluid cell image being an image obtained by performing full-sheet scanning on a cerebrospinal fluid cell smear; in response to a cell frame selection operation for the cerebrospinal fluid cell image, performing cell detection on a selected area, and performing frame selection positioning on cells detected in the selected area by using a square marking frame, the vertical distance between each edge of the square marking frame and the center of the cells being a preset distance; classifying the cells detected in the selected area by using a preset classification model to obtain classification information of the cells; obtaining color information corresponding to the classification information based on a preset mapping relation; and sequentially displaying the color blocks corresponding to the color information and the type names corresponding to the cells above the square marking frame.

The invention relates to the technical field of computers, in particular to a cell smear auditing method and device. The method comprises the following steps: presetting a specific cell type needing to be concerned for a cell smear; scanning the whole cell smear to obtain a cell image, and detecting the cell image by using an image detection algorithm; when a preset specific cell type is detected in the cell image, intercepting and counting the detected specific cells from the cell image, and recording position information of the specific cells in the cell image; and marking the specific cells based on the position information. According to the method, the cell image corresponding to the cell smear is detected by using the image detection algorithm, the specific type cells needing to be concerned are automatically identified and automatically counted, omission can be reduced, the integrity and accuracy of data are effectively improved, and the auditing efficiency of the cell smear is improved.

The present invention discloses a cervical cell detection and recognition method based on an attention mechanism and a detection transformer, including: inputting multiple cervical cancer cell source images into a preset convolutional network to extract image features; the preset convolutional network uses a 50-layer residual network combined with a self-attention mechanism as the backbone network; performing spatial position encoding on the source images; reducing the dimension of the extracted image features, and combining the spatial position encoding for transformer processing; inputting the processing results of the transformer into two feed-forward neural networks to respectively predict detection boxes and categories, and calculating a loss function based on this; updating network parameters by minimizing the loss function to obtain an optimal model; based on the optimal model, detecting the cervical cell source image to be detected and recognized, and realizing the positioning and classification of cervical abnormal cells. This method can screen cell smears, can well solve the low accuracy and limitations of manual film reading, has lower costs, less workload, and higher accuracy.

1. The name of the present design product: graphical user interface of cytological smear review software for electronic equipment. 2. The use of the present design product: for electronic equipment. 3. The design points of the present design product: the content of the graphical user interface. 4. The picture or photo that best indicates the design points: front view. 5. The design claimed contains color. 6. The use of the graphical user interface: for users to observe the picture obtained by scanning the cytological smear and its related item information as a whole, and to frame, mark and analyze the cells in the distribution diagram. 7. The human-computer interaction mode of the graphical user interface: the interface view can be artificially interacted, and the cell magnification can be enlarged through clicking and other interaction modes.

The invention provides a cell smear quality evaluation method and system based on cell morphology, a medium and a program product, and relates to the field of medical image processing and artificial intelligence. The method comprises the following steps: S1, acquiring an image of a cell smear, and carrying out preprocessing and multi-region labeling on the image of the cell smear; step S2, constructing a cell smear prediction model based on MSF-Net; the cell smear prediction model adopts ResNet to extract basic features of a cell smear image, and outputs a middle-high-level semantic feature map; the cell smear prediction model adopts a multi-branch parallel convolution architecture to perform multi-scale feature extraction on middle and high level semantic feature maps; step S3, carrying out Hybrid Attention operation on the fused feature map, and carrying out a hybrid Attention operation on the fused feature map; s4, taking the loss function as supervision when the cell smear prediction model is trained, and obtaining a trained cell smear prediction model; and S5, inputting the cell smear image of which the quality is to be evaluated into the cell smear prediction model, and outputting a corresponding quality evaluation result.

The utility model relates to a small-sized automatic dip dyeing device for a cell smear. The small-sized automatic dip dyeing device comprises a box body, a clear water tank, a sewage tank, a dyeing assembly and a moving assembly, the dyeing assembly comprises a slide rack, a dye liquor cylinder, a cleaning loop and an air drying cylinder; the slide frame is provided with a slide groove, and a slide can be vertically placed in the slide groove; the moving assembly comprises a lead screw module, a rotating motor module and a four-rod assembly, and the slide rack is fixedly connected with the four-rod assembly. Compared with the prior art, the device is small in size, can be placed in an operating room, and is low in dye consumption and high in dyeing efficiency and dyeing quality.

The invention discloses a full-automatic cell smear sample collecting device and system, relates to the technical field of cell smear collecting tools, and provides the following scheme that the full-automatic cell smear sample collecting device comprises a sample collecting cabinet, and a cell smear sample placing frame is arranged at the middle section position of an inner cavity of the sample collecting cabinet; a scraping action driving mechanism is arranged in the top area of an inner cavity of the sample collection cabinet, a plurality of wiping cotton clamping mechanisms inserted into the cell smear sample placement rack are arranged at the bottom of an outer ring of the scraping action driving mechanism, and a flushing mechanism is fixedly connected to the rear side end face of the sample collection cabinet. According to the technical scheme, the efficiency is improved in the scraping link compared with that of manual work, and a plurality of cell smears can be scraped at a time; the device has the advantages that the repeatability is high compared with that of manual work, the same scraping quality every time is ensured, and the efficiency is high; and the occurrence of sharp instrument injury caused by misoperation is avoided.

The present application relates to biomedical micro-imaging and cell pathology detection technical field, especially to a kind of alveolar lavage fluid macrophage terahertz near-field imaging identification method.Its technical scheme includes the following steps: the unstained alveolar lavage fluid cell smear sample is fixed on the object table, the sample is observed under bright field using optical microscope, the suspected micro area with volume difference or nuclear shape shadow characteristics is locked, and the near-field probe is focused to the suspected micro area;The suspected micro area is scanned in a large range using a terahertz near-field imaging system, and surface topography images and terahertz internal tomography images are obtained.According to the size characteristics of the target object in the image and the uniformity characteristics of the terahertz signal, the background interference cells are excluded.The present application provides a terahertz near-field imaging method that can quickly and objectively identify different physiological state macrophages without staining, based on the dual-mode signals of topography elevation and optical voltage.

The invention relates to the technical field of centrifugal machines, and discloses a cell smear centrifugal machine which comprises a machine box and further comprises a machine cover hinged to the top of the machine box through a hinge. An inner cavity is formed in the top of the case, and an inner container is mounted in the inner cavity; the centrifugal mechanism is arranged in the inner container and is used for centrifuging cell sap; and the reagent bottle is mounted on the centrifugal mechanism. According to the invention, through the cooperation of composite motion of revolution and rotation and a dynamic deflection mechanism, the single sedimentation mode of a traditional centrifuge is broken through, the centrifugal disc is deflected from a vertical storage state to a horizontal working state during revolution, and meanwhile, reagent bottles are rotated under the stirring of an L-shaped elastic plate, so that the reagent bottles are separated from the centrifugal disc; the compound motion generates a dynamic and three-dimensional stirring effect on the cell sap, so that cell agglomerates can be effectively scattered, cell aggregation or non-uniform sedimentation is prevented, a solid foundation is laid for preparing a high-quality smear with single-layer cell distribution and no overlapping, and the accuracy of subsequent pathological diagnosis is greatly improved.

The application discloses a TCT smear automatic detection system based on multi-level hard polarization feature fusion, which comprises a YOLO-TCT model, the YOLO-TCT model is obtained by improving YOLOv8, and the improvement lies in that a C2f module in a YOLOv8 backbone network is replaced by an MLHP-C2f module. Through an ablation experiment, it is proved that feature fusion when ML, PSA or HPSA is separately added on the basis of YOLOv8-L has a negative effect on the performance of the model, and only when ML and HPSA are combined, the model realizes the best mAP 0.5:0.95 and mAP 0.5 , which shows the rationality and superiority of the MLHP structure. The comparison experiment results of different models show that in the detection of high-resolution cervical cell TCT smear images, the detection accuracy of the YOLO-TCT is significantly better than those of other model systems.

An integrated constant-temperature fully-automatic cell smear preparation device includes a rotary settling disc, where the rotary settling disc includes a settling disc base and a turntable body connected to a settling disc body through a fixed shaft; a glass slide addition mechanism arranged adjacent to a glass slide inlet position of the rotary settling disc; a cleaning and sample addition integrated device, where the cleaning and sample addition integrated device is arranged on a side of the rotary settling disc, the cleaning and sample addition integrated device includes a cleaning assembly and a sample addition assembly, and the cleaning assembly and the sample addition assembly add fluid to one or more different settling cups simultaneously as the turntable body rotates intermittently; and a glass slide discharging mechanism arranged adjacent to a glass slide outlet position of the rotary settling disc.

The present application relates to a method, apparatus, computer device, and storage medium for analyzing the cell distribution state, including: obtaining a grayscale image of a cell smear as the cell image to be analyzed; obtaining the image texture features corresponding to the cell image; inputting the image texture features into a pre-trained distribution state analysis model, so as to, through the distribution state analysis model, determine the probability corresponding to each of at least two preset cell distribution states based on the image texture features, and determine the distribution state result according to the probability; and determining the cell distribution state corresponding to the cell smear according to the distribution state result output by the distribution state analysis model, thereby realizing the determination of the cell distribution state in the cell smear and being able to analyze the cell distribution uniformity in advance.

The present invention discloses a method for detecting, identifying and counting cerebrospinal fluid cell images. First, a high-quality digital image of a cerebrospinal fluid cell smear is obtained through a microscope. Then, the edges and other areas that distinguish cells in the image are revealed by calculating the gradient value. Furthermore, the local contrast change rate is calculated to accurately capture the microscopic changes in the cell image and effectively distinguish normal cells from cells with abnormal morphology. Then, the normal cells and abnormal cells are counted to obtain a counting result, which can better help medical staff identify the patient's condition and provide powerful patient medical record information for subsequent medical assistance.

This invention discloses an intelligent screening method and system for abnormal cells in cervical liquid-based cytology images, belonging to the field of medical image processing technology. The method includes: acquiring and preprocessing a full-field digital image of a liquid-based thin-layer cytology smear; extracting individual cell contours using a cell instance segmentation network; calculating morphological features such as nuclear area, nucleocytoplasmic ratio, chromatin distribution, and nuclear membrane regularity; sequentially distinguishing normal cells, atypical squamous cells, low-grade and high-grade squamous intraepithelial lesions using a cascaded classification strategy; locating abnormal cells and screening high-risk fields of view based on an attention-guided algorithm; and outputting an abnormal cell annotation atlas and TBS classification assistance suggestions.

The application discloses an abnormal cell detection method based on an improved YOLOv7 and Swin-Unet, which comprises the following steps: collecting pathological cell smear images, making an abnormal cell detection dataset and a segmentation dataset; building an improved YOLOv7 model and training the same; building a detection result screening module to classify cells in a detection network output image; building a Swin-Unet model and training the same for segmentation of an overlapping cell group image; using the improved YOLOv7 and Swin-Unet model for abnormal cell detection. The application fully utilizes context information during cell detection, effectively processes difficult-to-detect cell groups, and greatly improves the accuracy and recall rate under the premise of ensuring the detection rate.

The utility model relates to the technical field of cell smears, in particular to a centrifugal staining and sealing device, which is characterized in that a cell smear device is placed in the centrifugal staining device for centrifuging and staining operation, and after centrifuging and staining are completed, the stained cell smear device is sequentially subjected to disassembly, glue dripping and cover glass sealing by the sealing device. The traditional manual operation is replaced, so that the burden of the manual operation is reduced, the sample can be correctly separated and sealed, and standard cell slide preparation is realized.

The invention relates to the technical field of biomedical detection and pathological slide preparation, and discloses a reusable biocompatible silica gel cell smear preparation device and method.The reusable biocompatible silica gel cell smear preparation device comprises a sealing box, a slide positioning assembly is placed in the sealing box, and a plurality of adhesive glass slides used for cell sedimentation slide preparation are placed on the slide positioning assembly; a plurality of sedimentation assemblies for cell sedimentation are placed on the adhesive glass slide, a box cover is arranged above the sealing box, and a manual negative pressure assembly is arranged above the box cover. A'negative pressure source 'and a'sedimentation device' are separated in space, and a public negative pressure environment is constructed by utilizing a sealing box, so that a user can enjoy the efficiency improvement brought by negative pressure without changing any original operation habit, and the unification of'simplicity and convenience 'and'high efficiency' is really realized. According to the slide positioning assembly, through the mechanical design, one-hand, quick and blind operation fixing and releasing of the adhesive slide are achieved, and the efficiency of batch preparation is greatly improved.

The present invention relates to the technical field of pathological cell analysis, and in particular to a blood removal kit for pathological cytology and its usage method, which includes a blood removal reagent and a cell anti - detachment glass slide; the blood removal reagent includes alcohols, glacial acetic acid, sodium dihydrogen phosphate, disodium hydrogen phosphate, sodium chloride, a mucus softening agent, and deionized water. The reagents used are low - cost and are all common chemical reagents. The operation is simple and easy to understand, and it is applicable to various pathological cell blood - containing samples. When preparing pathological cell smears using the kit provided by the present invention, for blood - containing samples, it can effectively remove the interference of red blood cells and mucus components, enabling better cell enrichment, and maintaining the original morphology of diseased cells and normal cells. Most cells can be preserved on the glass slide during slide preparation, reducing the probability of slide preparation failure caused by cell detachment, improving the excellent slide rate of pathological cell slides, and enhancing the accuracy of pathological cytology diagnosis.

The invention discloses a cerebrospinal fluid cell examination report output method and device, computer equipment and a storage medium, and relates to the technical field of cerebrospinal fluid cell morphology examination.The cerebrospinal fluid cell examination report output method comprises the steps that a cerebrospinal fluid cell image is obtained, and the whole cerebrospinal fluid cell image is displayed; the cerebrospinal fluid cell image is an image obtained by performing full scanning on a cerebrospinal fluid cell smear; in response to a remark button for the cerebrospinal fluid cell image, providing a remark interface for a user to input corresponding remark information; in response to a frame selection operation for a target object on the cerebrospinal fluid cell image, marking the target object; after the target object is selected, in response to a selection operation for a description button of the target object, providing a description interface for a user to input corresponding description information, and displaying an image of the target object on the description interface; and in response to a picture interception button for the cerebrospinal fluid cell image, intercepting a picture of the current visual field of the cerebrospinal fluid cell image as a report alternative picture.

The utility model relates to the field of smear dyeing, in particular to a cell smear dyeing device for medical examination. The utility model provides a batch staining cell smear staining device for medical examination, which comprises a liquid collecting box, a staining table, connecting seats, connecting frames, an observation window, a supporting plate, a placing plate and the like, the staining table is arranged on the liquid collecting box, the connecting seats are rotatably connected to two sides of the staining table, the connecting frames are arranged on the connecting seats, and the observation window is arranged on the connecting frames. Observation windows are connected to the connecting frames, a plurality of supporting plates are evenly connected to the interior of the dyeing table at intervals, and a placement plate is rotationally connected between every two supporting plates. The cell glass slides are placed on the placing plates, then the quantitative water pump is started to perform cell dyeing, the quantitative water pump has an adjusting function, pushes the first guide rod to move and drives the shunt pipe to move downwards, so that the Swiss dye is accurately added to the cell glass slides, and batch dyeing can be performed by arranging the placing plates.

The invention relates to an unmarked cell smear preparation, polarization imaging and treatment method, which comprises the following steps: preparing an unstained cell smear through a cell specimen treatment and smear preparation step; performing full-polarization imaging on the unstained cell smear by adopting a muller microscope to obtain muller matrix image data of the cell smear; on the basis of the muller matrix image data, polarization substrate parameters are calculated, and polarization superpixels are extracted through an unsupervised clustering algorithm to be used for representing cell pathological features; and registering the polarization image of the unstained cell smear with the color image of the stained cell smear in the same area to generate multi-modal contrast data for auxiliary labeling and model training. According to the method disclosed by the invention, the cell smear does not need to be dyed, the microstructure characteristics of the sub-wavelength scale of the cell are captured through polarization imaging, and an automatic analysis technology is combined, so that a low-cost, high-efficiency and quantifiable technical tool is provided for cell pathology research.

Systems and methods herein provide a biomarker detection engine and its related functions. In an aspect, a biomarker detection engine receives a smear image of cells from a biopsy sample collected from a patient diagnosed with a myeloid malignancy. Responsive to receipt, the biomarker detection engine may preprocess the smear image to generate processed image data, for example by removing areas lacking cellular presence. Using the processed image data, the biomarker detection engine may generate, via one or more deep learning models, a prediction of a treatment outcome for a treatment therapy. The prediction may indicate whether the patient will be responsive to the treatment therapy. Based on the prediction, the biomarker detection engine may generate a recommendation for a treatment plan for the patient.