150 results about "Cell segmentation" patented technology

The invention provides a method and a device for classifying white blood cells. The method comprises the following steps: dyeing the white blood cells in a blood sample to obtain a blood sample containing the dyed white blood cells; performing image acquisition on the white blood cell blood sample to obtain a white blood cell blood sample image; segmenting various cells of the white blood cell blood sample image, and respectively extracting cell morphology characteristic parameters of various cells; performing re-segmentation on various segmented cells to obtain a cell nucleus image and a cytoplasm and particle image; extracting color characteristic parameters of the cell nucleus image; extracting particle distribution characteristic parameters and color characteristic parameters of the cytoplasm and particle image; performing normalization on extracted characteristics; sending the normalized characteristics into a neural network classifier, identifying five types of cells in the white blood cells, and respectively working out the number of the five types of cells and the percentage of total white blood cell count. According to the method and the device for classifying the white blood cells provided by the invention, the white blood cells can be accurately classified.

The invention relates to a cell image segmentation method based on automatic feature learning. As a method for learning features of cell images is very good in feature learning capacity, the cell segmentation accuracy can be greatly improved, and meanwhile, a random forest classifier does not need to select the features, so that the method is capable of well solving the confronted problems of feature extraction and selection in a recognition process. The cell image segmentation method based on the automatic feature learning comprises the following steps: 1, preprocessing: preprocessing initial cell images in a training set and a test set; (2) training a feature extractor; (3) performing recognition by utilizing the random forest classifier; and (4) postprocessing.

The invention discloses a method for segmenting a cervix uteri liquid base cell image. The method comprises the following steps of: 1, cell segmentation: performing illumination correction on an image, filtering noises and enhancing a cell boundary; and dividing the image into three types of cytoplasm, nucleus and background to eliminate a background class area; 2, nucleus segmentation: detecting centers of each of nucleuses in the cell area, estimating the approximate shapes of the nucleuses close to the centers of the nucleuses and correcting the shapes of the nucleuses to acquire an accurate boundary. The method is applied to cervix uteri cells and cell masses in a wide vision range, so that the phenomena of changed illumination, non-uniform dyeing and noise influence to a certain extent are avoided, and the cytoplasm, the single nucleus and adhesion nucleus can be segmented reliably and accurately.

The utility model discloses an adherent white blood cell segmentation method based on nucleus-marked watershed transformation. The adherent white blood cell segmentation method comprises the following steps: firstly inputting original RGB (Red, Green, Blue) images and discovering the generally difficult-to-solve problem of peripheral white blood cells and bone marrow white blood cells in the image processing process; secondly, carrying out HIS (Hue-Saturation-Intensity) and LUV color space and grayscale space conversion on the original images and analyzing the characteristics of each channel component image; thirdly, respectively carrying out threshold value segmentation and image subtraction on components B and grayscale images to obtain white blood cell images containing a part of impurities; fourthly, obtaining a target taking a white blood cell nuclei as a marker through an image enhancement technology; fifthly, carrying out morphological operation and watershed transformation on the white blood cell nuclei and the white blood cell images containing the impurities to remove the impurities, obtain accurate white blood cell images and solve the problem of cell adhesion; finally, cutting the targeted white blood cells, converting the targeted white blood cells into an LUV space, clustering the white blood cell images from the view of space and color and obtaining a white blood cell nucleus.

The invention belongs to the field of cell tracking, and discloses a method for synchronously tracking multiple cells in a high-adhesion cell environment. In a cell sequence image, how to divide and synchronously track the cells is an unsolved problem, and especially the problem of tracking and dividing the cells under the high-adhesion condition urgently needs to be solved. An improved dividing algorithm based on watersheds and multi-feature matching is firstly provided to achieve cell dividing, then a motion model suitable for Kalman filtering is built, the multi-feature matching is added to achieve cell predication and tracking. Through experimental verification, the method is effective, the average effective rate of dividing sequence frame cells is 94.4%, and the tracking effect is superior to that of the tracking method in the prior art.

The invention discloses a method for partitioning cytoplasm and cell nucleuses of white blood cells in a color blood cell image. The method includes the following steps that the background region besides the white blood cells and red blood cells in the color blood cell image is removed, and a binary image I only including the region of the red blood cells and the region of the white blood cells is obtained; the white blood cells and the background region in the color blood cell image are removed, and a binary image II only including the region of the red blood cells is obtained; the binary image II is subtracted from the binary image I, and a binary image III only including the region of the white blood cells is obtained; the region of the cell nucleuses in the color blood cell image is enhanced, and a binary image IV only including the area of the cell nucleuses is obtained; the binary image IV is subtracted from the binary image III, and the area of the cytoplasm is obtained. The method has the advantages that the partitioning algorithm is simple in calculation, the partition of the white blood cells and the red blood cells and the partition of the red blood cells and the cell nucleuses can be conducted at the same time, the time expenditure is reduced, and partition errors are removed so that partitioning results are more accurate.

A fast image region partition method receives a component labeled image and performs a two pass Zone Of Influence (ZOI) creation method to create a Zone Of Influence (ZOI) image. The two pass ZOI creation method performs a first pass scan to create a first pass intermediate distance image and a shortest distance component label image. It then performs a second pass scan using the first pass intermediate distance image and the shortest distance component label image to create a background distance transform image and a updated shortest distance component label image. An adaptive image region partition method receives a component labeled image and performs an adaptive two pass ZOI creation method to create an adaptive ZOI image. The distance lengths of the two pass adaptive ZOI creation method depend on their associated component labels. An adaptive cell segmentation method receives a nuclei mask image and a cell mask image. It performs adaptive nuclei region partition using the nuclei mask image to create adaptive nuclei mask ZOI. An adaptive cell region separation method uses the cell masks and the adaptive nuclei mask ZOI to generate adaptive cell separated regions. An adaptive dilation method receives an image and performs an adaptive background distance transform to create an adaptive background distance transform image. A threshold is applied to the adaptive background distance transform image to generate adaptive dilation image output. An adaptive erosion method receives an image and performs an adaptive foreground distance transform to create an adaptive foreground distance transform image. A threshold is applied to the adaptive foreground distance transform image to generate adaptive erosion image output.

The invention discloses an AML (Acute Myelocytic Leukemia) cell segmentation method based on Meanshift cluster and morphological operations. The algorithm is to cluster a bone marrow cell and a cell nucleus from two aspects of spatial distance and color distance, and is combined with a series of morphological operations and the modified watershed conversion technology, so as to solve the accurate segmentation problem of the adherent bone marrow cell and bone marrow cell nucleus. The algorithm is high in stability, and good in robustness for segmenting the adherent bone marrow cells with different AML types under different illumination conditions.

The invention discloses an aggregated white blood cell segmentation counting system. The system comprises an image acquisition module for dyeing white blood cells in a blood sample, dissolving red blood cells in the blood sample by using red blood cell lysate and acquiring a white blood cell image, an image preprocessing module used for performing image background removal on the white blood cellimage and obtaining an optimal segmentation threshold by using a maximum inter-class variance method and roughly segmenting a white blood cell region, an aggregated cell determination module used forobtaining a coarse segmentation image according to the rough segmentation of the white blood cell region, setting a discriminant function of a cell area and obtaining a multi-cell aggregation region,and an aggregated cell segmentation counting module used for extracting a cytoskeleton in each aggregation region and a gray curve at the cytoskeleton by using a morphological refinement method. According to the invention, by analyzing the gray scale characteristics of various white blood cell areas under a low power microscope, an adaptive threshold function is constructed, while a white blood cell count is obtained, the number of oxyphil cells is obtained, the cells in the aggregation region are quickly and accurately divided and counted, the method is quick and simple and is easy to implement.

The invention discloses a cervical cell image segmentation method based on an antagonistic generation network, comprising the following steps: a cell image is coarsely segmented, wherein for the cellimage coarse segmentation, a threshold method and a watershed algorithm are used for coarse segmentation of an original image to form guiding factors, and the original image is cut into small images;a virtual body segmentation image is generated, wherein the generated virtual body segmentation image is generated by using an antagonistic generation network designed in combination with a self-encoder, taking a clipped small image as an input, and using the guiding factors to help the neural network to locate a region of interest; a solid cell image is extracted, wherein the solid cell image extraction refers to that a real cell image is extracted from the clipped small image according to the virtual body segmentation image. The cervical cell image segmentation method based on the antagonistic generation network provided by the invention is the first time to use the antagonistic generation network to solve such problems, provides a novel automatic cell image segmentation method, and simultaneously solves the component loss in the traditional overlapped cell segmentation method.

The invention discloses a cervical cell pathological slice pathological cell segmentation method and system, in particular, an off-line training sample set of cervical cell pathological slice pathological cell is established, a multi-scale cavity convolution structure semantic segmentation network is introduced on the basis of a depth residual network, and the semantic segmentation model is trained. The unit to be identified is extracted from the cervical pathological slice image, and different types of pathological cells are segmented in the unit to be identified by using the trained semanticsegmentation model. Based on the morphological features of pathological cells, a contour deformation model is established to further optimize the semantic segmentation results. According to the cellnumber and confidence level of different pathological types, the pathological types of the whole slice are predicted. The invention utilizes semantic segmentation network model and deformation variational model to accurately segment different types of pathological cells on the cell pathological slice image, and simultaneously improves the recognition accuracy and the recognition efficiency.

The invention relates to a leukocyte positioning and segmentation method based on a deep neural network. The method comprises the following steps: S1, a feature extraction stage of designing an improved FPN for extracting multi-scale leukocyte features to form a multi-scale feature map; S2, a candidate region positioning stage of positioning a region where leukocytes may exist in the multi-scale feature map by using an RPN to obtain a candidate region; S3, a prediction stage of firstly, carrying out bilinear interpolation by utilizing a RoIAlign layer to align positioning results of candidateareas in a positioning stage, mapping each candidate area into a feature map with a fixed size, and then respectively inputting the feature map as a positioning branch and a segmentation branch to carry out final positioning and segmentation so as to realize leukocyte segmentation. The method provided by the invention not only can obviously improve the segmentation precision, but also has good robustness for blood cell images under different acquisition environments and preparation technologies.

The invention discloses a cell image segmentation method based on a Res2-UNeXt network structure, and the method comprises the steps: designing a network structure, and designing a proper and effective network according to the features of a cell image; adding a residual structure and a multi-scale convolution method into a U-Net network. The segmentation process comprises the following steps: obtaining a weight graph required for calculating Loss by utilizing a label graph of a training image; and inputting the original training data set into the Res2-NeXt network, and updating the parametersof the network according to the calculated loss; carrying out iterative training continuously until the precision of network prediction can reach a stable level; using a trained network to predict andinput new data to obtain a cell segmentation map. The invention provides a multi-scale network structure Res2-UNeXt, coarse-grained and fine-grained information can be better obtained, so that the segmentation performance of the method is improved.

The invention relates to a cell locating method and a cell dividing method. The cell locating method and the cell dividing method comprise the steps of conducting machine leaning on a first chromosomeimage containing cell locating information to obtain a prediction model, wherein the prediction model is used for a second chromosome image not containing the cell locating information and is used for predicting the cell locating information of the second chromosome image, and according to the cell locating information, conducting cell dividing on the second chromosome image. The cell locating method and the cell dividing method have the advantages of conducting automatic recognition in cell locating and cell dividing, not needing or reducing artificial identifications and saving time and labor.

A method, a computer readable medium, and a system are disclosed for cell segmentation. The method including generating a binary mask from an input image of a plurality of cells, wherein the binary mask separates foreground cells from a background; classifying each of the cell regions of the binary mask into single cell regions, small cluster regions, and large cluster regions; performing, on each of the small cluster regions, a segmentation based on a contour shape of the small cluster region; performing, on each of the large cluster regions, a segmentation based on a texture in the large cluster regions; and outputting an image with cell boundaries.

The invention discloses a semi-supervised learning cell segmentation method based on a generative adversarial network, which comprises the following steps: collecting cell segmentation data, preprocessing and enhancing the data, and dividing the data into a training set and a test set picture. A new adversarial generation network is designed by taking semi-supervised learning as a starting point.Compared with a previous adversarial generation network, the network replaces a generator with a small-parameter full-volume integral cut network and is used for outputting a probability graph to an input picture. For a cell picture without a label, a semi-supervised method is used for training a segmentation network, after initial segmentation prediction of an unmarked image is obtained from thesegmentation network, a segmentation prediction probability graph is transmitted through a discrimination network, and a confidence graph is obtained. The confidence map is used as a supervision signal, a self-learning mechanism is used to train a segmentation network, and the confidence map represents the quality of prediction segmentation. Through the convolutional neural network designed by theinvention, the cell segmentation accuracy is improved.

The invention discloses a single-cell image segmentation method. The method includes the following steps that: 1) image preprocessing is performed: an image is converted into a grayscale image, noisesare removed, and contrast enhancement is performed; 2) block threshold segmentation is performed so as to segment the image into A*A small blocks, the optimal threshold of each block is calculated byusing the OSTU, so that the foreground and the background of each block can be separated from each other; 3) whether nucleus state features obtained by the previous segmentation step are normal or not is judged, if the nucleus state features are normal, it is proved that a segmentation result is relatively good, and the result is outputted; 4) if the segmentation result does not conform to the nucleus state features, the result is an inaccurate segmentation result, a next step of image processing is performed; and 5) adaptive threshold segmentation is performed, the result of the adaptive threshold segmentation is outputted together with other normal segmented images. With the single-cell image segmentation method of the present invention adopted, the problems of inaccurate nucleus segmentation and slow segmentation speed can be solved. The single-cell image segmentation method combines the advantage of high speed of the block segmentation threshold segmentation and the advantages ofhigh accuracy and low workload of the adaptive threshold segmentation; and since the advantage of the block segmentation threshold segmentation and the advantages of the adaptive threshold segmentation are complementary, the quality of an output image can be improved.

The invention discloses a cell image segmentation method based on a particle swarm neural network. The method comprises following steps of inputting 3*3 windows to replace a traditional single pixel channel; adopting a method based on information entropy to determine the quantity of hidden layer neural elements; selecting activation functions of each layer; simplifying weight training to be an optimization problem; using an improved particle swarm to optimize and solve the problem; carrying out a network training; and analyzing test results. According to the invention, the method is improved based on the traditional BP neural network, so cell images can be well segmented; problems about how to determine the network structure and how to ensure that the network is converged to be overall optimal are solved; segmentation effects of the cell images are improved; and time loss in the cell segmentation process is relatively reduced.

A thin film type solar cell and a method for manufacturing the same is disclosed, which can overcome various problems caused by a related art laser-scribing procedure since the thin film type solar cell is divided into a plurality of sub-cells through the use of auxiliary electrode or partition wall, the thin film type solar cell comprising a substrate; a front electrode layer and a cell-dividing part on the substrate; and a rear electrode on the semiconductor layer.

The invention discloses a mammary glandular cell segmentation method based on a multi-scale growth and double-strategy adhesion-removing model. The method comprises the following steps: firstly, inputting a mammary glandular tissue image and converting the image into a gray image; secondly, enhancing the contrast ratio; thirdly, carrying out cell positioning by using wavelet decomposition; fourthly, carrying out multi-scale region growth; fifthly, realizing primary segmentation of a cell region through voting and selecting; sixthly, judging whether the segmented region has cell adhesion or not; if the cell adhesion does not exist, determining that the segmented region is a single cell region, and outputting a segmentation result; if the cell adhesion exists, determining that the segmented region is an adhesion region, and carrying out adherent cell segmentation; and finally, carrying out adherent cell segmentation by using the double-strategy adhesion-removing model constructed by morphological corrosion-expansion operation and a corner detection segmentation algorithm until all the cells are segmented. By virtue of the method, the influences on mammary glandular cell segmentation, caused by a complicated background of a mammary glandular tissue slice image, are effectively inhibited; and the identification precision of an adherent cell segmentation line is improved and the segmentation precision of the adherent cells is further improved.

The invention provides a cell detection segmentation system and method based on a deep learning neural network. A deep learning method is used for detecting a cell pathological image. Normal cells, inflammatory cells, trichomonad cells, atrophy cells, HPV viruses and other cells in the picture are segmented out. Each type is marked and the number of each type is counted. A judgment is made as to whether a patient is infected or inflammatory or not and reliable and efficient auxiliary diagnosis is provided for pathologists. The invention has the advantages of simplicity, effectiveness, less required hardware configuration and low implementation cost.

The invention relates to a cell image segmentation method and device, computer equipment and a storage medium. The method comprises the following steps: reading a cell grayscale image; carrying out histogram equalization operation on the cell grayscale image to obtain an equalized image; performing morphological operation on the equalized image to obtain a morphological image, wherein the morphological operation comprises top cap operation and gradient operation; detecting cell edges in the morphological image through an edge detection algorithm to obtain a cell edge image; carrying out binarization processing on the cell edge image to obtain a binarized cell image; and carrying out cell segmentation according to the binarized cell image to obtain a cell segmentation image. By adopting themethod, the accuracy of cell image segmentation can be improved.

The invention relates to a system and method for realizing electrical layer linear protection in POTN, relating to the POTN field. A business mapping unit of a source end converts ODUk channel data into a group of cells through cell segmentation, a multicast ID is distributed, the cells are subjected to concurrence or selection at work and protection light channel units through a cell switching unit, and after the cells are received by the work and protection light channel units, the cells are selectively activated and are sent to the corresponding cell reception ports; after the work and protection light channel units of a destination end receive signals, the de-mapping and de-multiplexing of ODUk is completed, the cells are sent out via the corresponding channels, a system cross is established to point to the business mapping unit; and the signal failure, signal deterioration, and APS overhead information are detected, an APS control unit notifies the current needed light channel units to activate the cross and non-needed light channel units to block the cross. The ODUk electrical layer linear protection is realized under the unified cell exchange configuration of POTN, and the high effectiveness and the reliability are guaranteed.

The invention discloses a single cell sorting device and method based on image processing and ink-jet printing. The single cell sorting device comprises a micro-fluidic chip, an image acquisition device, an image processing and control unit, a displacement actuator, a liquid container and a displacement table, Liquid containing cells flows in a pipeline in the micro-fluidic chip under the drive ofpressure, when the image acquisition device shoots and recognizes a target object needing to be screened, the control unit drives the displacement actuator to generate the action of knocking the chip, micro-droplets containing single cells are printed out from a nozzle of the micro-fluidic chip, and in combination with the displacement table, different target cells are divided into different droplets. The microfluidic cell printing technology provided by the invention is combined with an in-situ image detection technology, so that high-precision cell sorting can be realized.

The invention discloses a random weight network partitioning method for a blood leukocyte microscopic image. The automatic partitioning technology is composed of four sub-processes of category coding and training library establishment, random weight network training, decoding partitioning and morphological operator repair, blood leukocyte partitioning is converted into classification, the leukocyte microscopic image is automatically partitioned in a classified mode, and integral and communicated cytoplasm and cell nucleus zones are acquired. The method has the advantages that the effective categories of pixel points of the blood leukocyte image are coded, a stable blood leukocyte classification training library is established, an optimal coding decision making model is acquired through a quick and efficient random weight network, an optimal code of the leukocyte image to be partitioned is acquired, and a final partitioning result is acquired. By the adoption of the method, the leukocyte microscopic image is efficiently partitioned.

The invention relates to a primary tumor cell segmentation and recognition method and system based on depth learning, which is characterized in that the method comprises a model construction module, amodel training module and a model prediction module. the model building module is used to build the depth full convolution neural network model based on the artificial neural network in depth learning; The model training module is used to train the deep total convolution neural network model according to the training set, and the trained deep total convolution neural network model is obtained. The model prediction module is used to input the original image segmentation into the trained depth full convolution neural network model, and the segmentation results of cancer cell regions of each segmented image are aggregated to obtain the segmentation results of cancer cell regions of the original image. The invention has high accuracy and can be widely applied in the field of biomedical imageprocessing.

The invention relates to a cell image semantic segmentation method fusing image segmentation and classification. The method comprises: preprocessing cell image data and then processing the cell imagedata through a bilinear fine-grained classification neural network, an OSTU algorithm and a filling algorithm, and then respectively obtaining a cell classification model and a cell segmentation map;and predicting a foreground connected region of the cell segmentation map by the cell classification model, assigning a prediction result to the connected region so as to obtain a region-by-region classification result, and finally obtaining a semantic segmentation result of the cell test image in combination with a background region obtained by segmentation. A traditional threshold method and a deep learning method are fused to achieve accurate semantic segmentation of the cell image. Compared with a traditional cell image segmentation method, the cell image semantic segmentation method is advantageous in that semantic information of cells can be obtained, the semantic information is of a pixel-by-pixel semantic category, and the method can be applied to identification and isolation of cell contamination.

The embodiment of the invention provides a cell image segmentation method and device. The method comprises the steps of obtaining a cell image to be segmented; inputting the cell image to be segmented into a cell segmentation model to obtain a cell segmentation result outputted by the cell segmentation model, wherein the cell segmentation model is obtained by training an enhanced U-Net network based on a sample cell image and a real label image corresponding to the sample cell image, the enhanced U-Net network is a neural network in which the number of network layers is increased in an initial U-Net network, and a BN layer is added to the network. According to the method and the device provided by the embodiment of the invention, the segmentation effect of the overlapping cells and the adhesion cells is improved based on the initial U-Net network, the cell segmentation accuracy is optimized, while the model training is accelerated based on the BN algorithm, and the model performance is optimized. By inputting the to-be-segmented cell image into the cell segmentation model obtained by training, the rapid, accurate, simple and convenient cell segmentation can be realized.

The invention discloses a gland cell image segmentation method and system based on an improved U-Net network. According to the method, the convolution layers are combined to construct the dense connection block, and the U-Net is amplified by a multi-resolution analysis method, so that the problem of cell segmentation with different rules can be well solved. And a self-attention module, namely a position attention module and a channel attention module, is introduced at a decoder end, so that context information can be adaptively aggregated, and the feature representation of cell segmentation isimproved. The cell image is segmented by using the network, so that the segmentation effect is improved. The method is easy to implement, data preprocessing operation is simple, and better robustnessand accuracy are achieved.

The invention belongs to the technical field of basic laboratory science, and discloses a white blood cell image processing method and system based on the subtraction of connected area. Each individual connected area forms an identified block for marking white pixels in a binary image. After the connected region is marked, the area of each connected region is obtained, and the connected region whose area is less than a certain value is deleted by using the MATLAB function bwareaopen. In the original image of granular and non-granular leukocytes, a classic and useful image segmentation method-Dam algorithm is utilized, i. e. Watershed, divides and counts non-granular leukocytes, removes the non-granular leukocytes from the original image using the function imsubtract to obtain an image containing only granular leukocytes, and divides the total granular leukocyte area by the average area to obtain the granular leukocyte count. The invention can clearly distinguish granular leukocyte fromnon-granular leukocyte, has clear image and accurate counting.