34 results about "Segmented cell" 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 method for segmenting cervical cancer cells. The method includes the following steps that noise of a cervical image is eliminated; a cytoplasm template is constructed for the image of which the noise is eliminated to perform rough segmentation, so that a cytoplasm area is obtained through segmentation; super-pixels are calculated for the cytoplasm area obtained through segmentation; the cytoplasm area which the super-pixels are calculated for is classified by the adoption of a convolution neural network; according to the constructed cytoplasm template of the image of which the noise is eliminated, cell nucleuses are roughly segmented; the roughly segmented cell nucleuses are corrected, and therefore segmentation on the cervical cancer cells is finished. The invention further relates to a system for segmenting the cervical cancer cells. On one hand, processing speed is guaranteed, and on the other hand, an accurate segmentation effect is achieved.

A magnetic tunneling junction (MTJ) memory cell for a magnetic random access memory (MRAM) array is formed as a chain of magnetostatically coupled segments. The segments can be circular, elliptical, lozenge shaped or shaped in other geometrical forms. Unlike the isolated cells of typical MTJ designs which exhibit curling of the magnetization at the cell ends and uncompensated pole structures, the present multi-segmented design, with the segments being magnetostatically coupled, undergoes magnetization switching at controlled nucleation sites by the fanning mode. As a result, the multi-segmented cells of the present invention are not subject to variations in switching fields due to shape irregularities and structural defects.

The invention discloses an unsupervised cervical cell image automatic segmentation method. The method comprises the following steps of 1) preprocessing a cervical cell image; 2) subjecting the preprocessed cell image to the pre-background rough segmentation, and extracting a region to which cells belong; 3) subjecting the roughly segmented cell image to the detection and segmentation of cell components, and segmenting cells of different types by using a rapid region convolution neural network; 4) detecting and segmenting the cell nucleuses of cervical cells; 5) according to the characteristic parameters of the cell nucleuses, screening the cell nucleuses to obtain final candidate cell nucleuses; 6) judging whether the cell types obtained in the step 3) are multicellular spheroids or not; if not, segmenting a cytoplasmic region by using an activity contour model and a prior template; otherwise, conducting the step 7); 7) conducting the post-treatment based on the segmentation result of cell nucleus and cytoplasm, and the domain knowledge. In this way, the effective segmentation of a whole cervical cell is completed.

A magnetic tunneling junction (MTJ) memory cell for a magnetic random access memory (MRAM) array is formed as a chain of magnetostatically coupled segments. The segments can be circular, elliptical, lozenge shaped or shaped in other geometrical forms. Unlike the isolated cells of typical MTJ designs which exhibit curling of the magnetization at the cell ends and uncompensated pole structures, the present multi-segmented design, with the segments being magnetostatically coupled, undergoes magnetization switching at controlled nucleation sites by the fanning mode. As a result, the multi-segmented cells of the present invention are not subject to variations in switching fields due to shape irregularities and structural defects.

The invention discloses a segmentation method for unconventional cells in a pathological section. The method comprises the steps that cells in the pathological section are processed into separate to-be-segmented cell images with a transparent background, and a pixel tag is allocated to each pixel point of each to-be-segmented image; a mapping method is used to randomly distribute the to-be-segmented cell images on a white background, the cells are superposed according to a certain probability to form pseudo-input images, and corresponding full-image pixel tags are acquired and marked as real-value tags; the pseudo-input images and the real-value tags are used as training data to train a Mask-RCNN, so that the Mask-CNN has the abilities of detecting an unconventional cell boundary box and predicting the pixel tags in the box; and a new pathological section not marked is input into the converged Mask-RCNN, the unconventional cells in the non-segmented pathological section are detected, and a final segmentation result is obtained through postprocessing. Through the segmentation method, marking time can be effectively shortened, marking cost can be effectively lowered, a large amount of training data can be generated in a short time, and fitting can be well performed on a large amount of data.

The invention discloses a white blood cell segmentation method based on super pixels and an anomaly detection color blood cell image. The method includes the steps that firstly, CMYK and HIS color space of an original color blood cell RGB image is combined with image airspace information, a seven-dimension feature vector is established, an image is pre-segmented by an SLIC superpixel partitioning algorithm, and a superpixel segmentation image is obtained; secondly, a cell nucleus area is detected by using an abnormal target detection method, an abnormal energy value image of each pixel point is obtained, and a pre-segmented cell nucleus area image is obtained after area smoothing and threshold segmentation are conducted; finally, corresponding superpixel areas of the pre-segmented cell nucleus area image and the superpixel segmentation image are combined, as for H component of white blood cell HSI space, surrounding pixel points of a cell nucleus are selected to serve as seed points to conduct area growing, the surrounding pixel points are combined with a pre-segmented superpixel image, and white blood cells are segmented out. The segmentation algorithm is simple, the segmentation speed is high, part space information is adopted during segmenting, and the segmentation is more accurate.

Disclosed are electrochemical devices, such as lithium ion battery electrodes, lithium ion conducting solid-state electrolytes, and solid-state lithium ion batteries including these electrodes and solid-state electrolytes. Also disclosed are methods for making such electrochemical devices. In particular, a segmented cell architecture disclosed herein enables solid state batteries to be flexible and capable of assuming a rolled or folded stack structure.

An automatically operating apparatus designed as a table-top apparatus for the reproducible production of cell or tissue samples to be examined and arranged on specimen slides comprises, located its center, a rotatably supported, advance device having arranged on its periphery a plurality of modular processing stations at a distance from the advance device. Receiving devices provided in the peripheral region of the advance device are disposed to receive specimen slides on which automatically segmented cell and tissue segments can be positioned in a reproducible and correctly aligned manner. The cell and tissue segments are durably fixed in position on the specimen slides with the use of a curable adhesive, and the specimen slides, after being delivered, are subjected to further treatment processes in a further treatment device.

The invention discloses an immunohistochemical pathological image CD3 positive cell nucleus segmentation method and a system, and the method comprises the steps: carrying out the color deconvolution of an immunohistochemical pathological image, and separating a staining channel; segmenting the image into irregular pixel blocks by adopting superpixels, carrying out kmeans clustering to distinguishan image background, and removing the image background; performing image segmentation based on the morphological characteristics to obtain a preliminarily segmented cell nucleus first region image L1and a to-be-processed first image C1; performing local threshold bernsen segmentation and morphological feature segmentation on the first image C1 to be processed to obtain a segmented cell nucleus second region image L2 and a second image C2 to be processed; performing foreground marking on the second image C2 to be processed, and segmenting a third region image L3 of the cell nucleus by adoptinga watershed algorithm; and forming a cell nucleus segmentation image by the cell nucleus first region image L1, the cell nucleus second region image L2 and the cell nucleus third region image L3. Themethod is high in robustness and accurate in segmentation, and can meet the requirements of practical application.

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.

An accurate cell nucleus segmentation method comprises the following steps: firstly, obtaining image data containing cell nuclei, and then carrying out pre-processing filtering operation on an image; carrying out preliminary segmentation on the cell nucleus by using a binary clustering algorithm; the influence of randomness of initial clustering selection on a segmentation result is reduced; selecting specific areas containing respective colors at the target and the background to iteratively update respective clustering centers, classifying all pixel points in the filtered image by using the obtained target clustering center and background clustering center as standards, judging whether each pixel point belongs to a target class or a background class, and finishing preliminary cell nucleus segmentation; repairing the preliminarily segmented cell nuclei, removing impurities, and performing accurate contour fitting on the cell nuclei by adopting a level set method; carrying out blocking operation of a partial overlapping area on the cell nucleus image subjected to preliminary segmentation, repairing and impurity removal, carrying out level set iteration on each block, and restoring the image according to a result to obtain an accurately segmented cell nucleus image.

The invention provides a high density cell tracking method based on topological constraint and a Hungarian algorithm, which comprises: (1) segmenting a cell image sequence by using an image segmentation method which combines a level set algorithm and a local gray threshold process, and initially labeling segmented cells in each frame; (2) according to distance limitation, establishing a tracking search region for a cell to be matched in the kth frame in the k+1th frame, and listing the cells in the region as candidate cells; (3) establishing a coefficient matrix Q, and if a cell j in the k+1th frame is the candidate cell of a cell i in the kth frame, performing data association according to topological constraint to calculate the similarity Qij of the cell j, or assigning a larger value to the similarity of the cell j; (4) performing transformation on the coefficient matrix by using the Hungarian algorithm to find out independent zero elements, wherein the cells represented by the rows of the zero elements are matched; (5) finding out rows in which there are no zero elements after matrix transformation, and taking the cells corresponding to the rows into consideration respectively; and (6) adding 1 to the k, jumping to the step 2, and repeating the steps till the last frame of the image sequence. The method can realize high-efficiency cell tracking.

The invention discloses a synechia cell image segmenting method based on a polyphase mutual exclusion level set. The circle centers of all cells are acquired through carrying out Hough transformation circle detection to quasi-circle cells in a microscopical cell image; a small circle is automatically set according to the circle center of every cell; each small circle is taken as an initial curve; independent evolution is carried out to a synechia cell area under the effect of mutual exclusion energy according to the guidance of image gradient information and the mode of simultaneously evoluting multi-level functions; mutual exclusion among different closed curves can be ensured; therefore, the synechia cell image is segmented; the problem that the traditional segmenting method cannot segment synechia crowded cell group areas is solved; and the method of the invention is advantaged by that the processing steps are few, the segmented cell outlines are natural and the method is applicable for segmenting and counting the quasi-circle cell image, has high measurement precision and strong adaptive capacity.

The invention relates to an HCC pathological image-oriented cell nucleus segmentation and classification method. The method comprises the steps of reading an original HCC image; performing k-means clustering on the image to obtain segmented cell nucleuses; performing refinement on the segmented cell nucleuses by using morphological operation, performing registration in three aspects, and performing calculation through four similarity parameters together with a cell nucleus shape library manually selected by a pathologist to obtain a cell nucleus shape feature matrix; according to the registered cell nucleuses, calculating cell nucleus boundary characteristics to obtain a cell nucleus boundary characteristic matrix; and fusing the cell nucleus shape feature matrix with the cell nucleus boundary characteristic matrix, and performing classification in a random forest classifier to obtain a result. The cell nucleuses are segmented by using the k-means clustering and the morphological operation; and the cell nucleuses are classified and identified through the proposed shape and boundary characteristics, so that the classification accuracy of each type of cell nucleuses is improved, theconditions of more cells are considered, and higher pertinence is achieved.

The invention discloses a co-culture device for cell culture and cell-cell interaction and a using method of the co-culture device. The device comprises a culture plate, wherein the culture plate is provided with at least one culture hole, at least one detachable semipermeable membrane spacing block and detachable spacing blocks; each detachable semipermeable membrane spacing block divides the corresponding culture hole into a plurality of cell culture rooms; and the detachable spacing blocks are positioned on two sides of each detachable semipermeable membrane spacing block. The using method of the device comprises the following steps: inserting the detachable semipermeable membrane spacing blocks and the detachable spacing blocks in the culture holes after sterilization; culturing tumor cells in a segmented cell culture room; culturing adherent cells in another cell culture room; detaching the detachable spacing blocks, and enabling the tumor cells and the adherent cells to be in co-culture; and continuing co-culture, observing a tumor cell balling condition and a migration condition of the balled tumor cells from one cell culture room to the other cell culture room. The co-culture device for cell culture and cell-cell interaction is simple in structure, simple and practical in operation, and visual and clear in effect.

The present invention is to provide an optical surface defect inspection apparatus or an optical surface defect inspection method that can improve a signal-to-noise ratio according to a multi-segmented cell method without performing autofocus operations, and can implement highly sensitive inspection. The present invention is an optical surface defect inspection apparatus or an optical surface defect inspection method in which an inspection beam is applied onto a test subject, an image of a scattered light from the surface of the test subject is formed on a photo-detector, and a defect on the surface of the test subject is inspected based on an output from the photo-detector. The photo-detector has an optical fiber bundle. One end thereof forms a circular light receiving surface to receive the scattered light. The other end thereof is connected to a plurality of light receiving devices. The optical fiber bundle is divided into a plurality of fan-shaped cells in the light receiving surface, and connected to the light emitting devices in units of the cells for performing the inspection based on the outputs of the plurality of cells.

The invention provides a cell edge segmentation method and device based on adaptive morphology, and the method comprises the steps: carrying out the instance segmentation of a to-be-segmented cell image through a cell segmentation model, and obtaining an initial segmentation result; based on the statistical characteristics of the cells in the initial segmentation result, performing adaptive iterative corrosion processing on the initial segmentation result to obtain an optimal corrosion result corresponding to the to-be-segmented cell image; wherein convolution parameters in the self-adaptive iterative corrosion treatment process can be reduced along with reduction of the difference between the statistical characteristics of the cells in the initial segmentation result and the statistical characteristics of the cells in the current corrosion result, and the statistical characteristics of the cells in the optimal corrosion result are matched with the statistical characteristics of the cells in the initial segmentation result; and performing fine segmentation on the initial segmentation result based on the optimal corrosion result by using a watershed algorithm to obtain a final segmentation result. According to the method, the smooth edge which is more accurate and more in line with the original form of the cell can be segmented, and the accuracy of cell edge segmentation is improved.

The invention belongs to the technical field of biomedicine and computer image processing, and discloses a cell image segmentation method based on graph path search and deep learning, and the method comprises the following steps: employing a trained U-net prediction model, and carrying out the following steps: in a prediction stage, inputting a to-be-segmented cell image into the trained U-net prediction model, and predicting a distance graph of a to-be-segmented cell; labeling a cell center, and taking the pixel point with the maximum local pixel value as the cell center; searching paths, searching a plurality of paths of two adjacent cell centers, and extracting pixel values of path points; carrying out judging, comparing the pixel value of each path point on the search path with the pixel value of the cell center to judge whether the two cell centers belong to different cells or not, if not, carrying out path search between the other two adjacent cell centers, and if so, carrying out segmentation processing, and repeatedly searching until all the search is finished. According to the invention, the adherent cells in the cell image can be well distinguished and segmented.

An automatically operating apparatus designed as a table-top apparatus for the reproducible production of cell or tissue samples to be examined and arranged on specimen slides comprises, located its center, a rotatably supported, advance device having arranged on its periphery a plurality of modular processing stations at a distance from the advance device. Receiving devices provided in the peripheral region of the advance device are disposed to receive specimen slides on which automatically segmented cell and tissue segments can be positioned in a reproducible and correctly aligned manner. The cell and tissue segments are durably fixed in position on the specimen slides with the use of a curable adhesive, and the specimen slides, after being delivered, are subjected to further treatment processes in a further treatment device.

The embodiment of the invention discloses a cell image segmentation method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring a to-be-segmented cell image; inputting the to-be-segmented cell image into a preset generative adversarial network to obtain a mask image; obtaining an instance center mark of the to-be-segmented cell image according to the mask image; and according to the mask image and the instance center mark, based on a preset image segmentation algorithm, obtaining a target segmentation image of the to-be-segmented cell. The to-be-segmented cell image is input into the preset generative adversarial network model, the mask image of the to-be-segmented cell image is automatically generated, and the cell nucleus of the to-be-segmented cell image is labeled, so that cell nucleus segmentation is performed on the to-be-segmented cell image, manual cell nucleus labeling on the to-be-segmented cell image is avoided, manual operation steps are reduced, and the cell segmentation efficiency and precision are improved.

The invention provides a cell segmentation method and device based on a multi-layer structure and electronic equipment. The method comprises the following steps: acquiring a to-be-segmented cell image; preprocessing the cell image to obtain a preprocessed image; performing coarse segmentation on the preprocessed image by adopting a watershed algorithm and an improved GVF Snake model to obtain a cell coarse contour; and performing fine cell segmentation on the coarse cell contour by combining convex hull detection, angular point detection and ellipse fitting to obtain a cell contour. According to the scheme, cell segmentation of a multi-layer structure is completed through pretreatment, coarse segmentation and fine segmentation, the cell segmentation precision is high, and the efficiency is high.

The invention provides the application of the compound MG132 in preparing the drug to synergistically promote the retinoic acid drug for the differentiation induction therapy of leukemia. The molecular formula of the compound MG132 is C26H41N3O5, the concentration of the compound MG132 is 1*10<-8> to 1*10<-6>M, and the concentration of the retinoic acid is 1*10<-9> to 1*10<-5>M. The compound MG132 with the single effect can not induce the leukemia cells to be differentiated, but promote the differentiation induction effect of the retinoic acid drug on the leukemia cells, which is presented as the promotion of the anti-proliferative effect and the cell cycle arresting effect of the retinoic acid drug on the leukemia cells, promote the expression of the differentiation specific antigen CD11b on the leukemia cell surface, and increasing the number of segmented cells. The invention opens up the new drug application field of the compound MG132.

The invention discloses an unsupervised cervical cell image automatic segmentation method. The method comprises the following steps of 1) preprocessing a cervical cell image; 2) subjecting the preprocessed cell image to the pre-background rough segmentation, and extracting a region to which cells belong; 3) subjecting the roughly segmented cell image to the detection and segmentation of cell components, and segmenting cells of different types by using a rapid region convolution neural network; 4) detecting and segmenting the cell nucleuses of cervical cells; 5) according to the characteristic parameters of the cell nucleuses, screening the cell nucleuses to obtain final candidate cell nucleuses; 6) judging whether the cell types obtained in the step 3) are multicellular spheroids or not; if not, segmenting a cytoplasmic region by using an activity contour model and a prior template; otherwise, conducting the step 7); 7) conducting the post-treatment based on the segmentation result of cell nucleus and cytoplasm, and the domain knowledge. In this way, the effective segmentation of a whole cervical cell is completed.

The invention discloses a symmetrical double-cathode structure battery and a preparation method and a discharge method thereof, and the symmetrical double-cathode structure battery comprises a battery upper cathode plate, a battery lower cathode plate, a battery left anode plate, a battery right anode plate, a first current lead-out rod, a first battery connecting piece, a first segmented battery and a second segmented battery, the battery upper cathode plate is buckled on the battery lower cathode plate, and a battery left anode plate, a first sectional battery, a first battery connecting piece, a second sectional battery and a battery right anode plate are clamped between the battery upper cathode plate and the battery lower cathode plate; a first current lead-out rod penetrates through one ends of the battery left anode plate, the first battery connecting piece and the battery right anode plate, a first upper groove is formed in the battery upper cathode plate to avoid the first battery connecting piece, and a first lower groove is formed in the battery lower cathode plate to avoid the first battery connecting piece. According to the symmetrical double-cathode structure battery provided by the invention, the problem of concentration polarization caused by current collecting area difference in cathode and anode discharge reaction can be solved.

The present invention is to provide an optical surface defect inspection apparatus or an optical surface defect inspection method that can improve a signal-to-noise ratio according to a multi-segmented cell method without performing autofocus operations, and can implement highly sensitive inspection. The present invention is an optical surface defect inspection apparatus or an optical surface defect inspection method in which an inspection beam is applied onto a test subject, an image of a scattered light from the surface of the test subject is formed on a photo-detector, and a defect on the surface of the test subject is inspected based on an output from the photo-detector. The photo-detector has an optical fiber bundle. One end thereof forms a circular light receiving surface to receive the scattered light. The other end thereof is connected to a plurality of light receiving devices. The optical fiber bundle is divided into a plurality of fan-shaped cells in the light receiving surface, and connected to the light emitting devices in units of the cells for performing the inspection based on the outputs of the plurality of cells.

The invention provides a high density cell tracking method based on topological constraint and a Hungarian algorithm, which comprises: (1) segmenting a cell image sequence by using an image segmentation method which combines a level set algorithm and a local gray threshold process, and initially labeling segmented cells in each frame; (2) according to distance limitation, establishing a tracking search region for a cell to be matched in the kth frame in the k+1th frame, and listing the cells in the region as candidate cells; (3) establishing a coefficient matrix Q, and if a cell j in the k+1th frame is the candidate cell of a cell i in the kth frame, performing data association according to topological constraint to calculate the similarity Qij of the cell j, or assigning a larger value to the similarity of the cell j; (4) performing transformation on the coefficient matrix by using the Hungarian algorithm to find out independent zero elements, wherein the cells represented by the rows of the zero elements are matched; (5) finding out rows in which there are no zero elements after matrix transformation, and taking the cells corresponding to the rows into consideration respectively; and (6) adding 1 to the k, jumping to the step 2, and repeating the steps till the last frame of the image sequence. The method can realize high-efficiency cell tracking.

The invention provides application of a CDK2 antagonist in preparation of sensitization drugs of induction differentiation therapy drugs. The CDK2 antagonist inhibits CDK2 gene transcription and / or translation and / or kinase activity, and is siRNA and small molecule chemical inhibitor specific to CDK2. Studies show that the CDK2 antagonist has an induction differentiation effect on leukemia cells, at the same time also promotes the induction differentiation effect of retinoic acid drugs on leukemia cells, and promotes the proliferation inhibition ability on leukemia cells, expression of cell surface differentiation specific antigen CD11b, enhancement of NBT reduction ability and increase of segmented cell number. The CDK2 antagonist involved in the invention is in favor of improving the sensitivity of tumor cells to differentiation therapy drugs, strengthening the differentiation therapy effects, reducing chemotherapy drug dosage, alleviating the toxic and side effects of chemotherapy drugs on human normal cells, and improving the quality of life of tumor patients, thus having good application prospects in the therapy field of leukemia and other tumors.

The invention discloses a white blood cell segmentation method based on super pixels and an anomaly detection color blood cell image. The method includes the steps that firstly, CMYK and HIS color space of an original color blood cell RGB image is combined with image airspace information, a seven-dimension feature vector is established, an image is pre-segmented by an SLIC superpixel partitioning algorithm, and a superpixel segmentation image is obtained; secondly, a cell nucleus area is detected by using an abnormal target detection method, an abnormal energy value image of each pixel point is obtained, and a pre-segmented cell nucleus area image is obtained after area smoothing and threshold segmentation are conducted; finally, corresponding superpixel areas of the pre-segmented cell nucleus area image and the superpixel segmentation image are combined, as for H component of white blood cell HSI space, surrounding pixel points of a cell nucleus are selected to serve as seed points to conduct area growing, the surrounding pixel points are combined with a pre-segmented superpixel image, and white blood cells are segmented out. The segmentation algorithm is simple, the segmentation speed is high, part space information is adopted during segmenting, and the segmentation is more accurate.