109 results about "Cell feature" patented technology

The invention relates to the technical field of model analysis, in particular to an imaging flow cytometry cell detection method based on an improved model. The method comprises the following steps: introducing a cell sample to be detected into an imaging flow cytometry system integrated with a micro-fluidic chip for continuous image acquisition to generate an initial cell image sequence; an automatic digital focusing algorithm is applied to the initial cell image sequence, and a cell image frame set with the optimal focal plane is screened out; inputting the cell image frame set into a preset PA-YOLO improved model for multi-dimensional extraction and fusion, and generating a multi-scale cell characteristic spectrum; carrying out refined feature learning and cell target positioning and classification on the multi-scale cell feature spectrum, and outputting a cell detection result; and carrying out validity verification on the cell detection result, and carrying out comparative analysis in combination with an imaging flow cytometry system to generate a cell detection report. According to the method, the imaging quality and the detection accuracy of cell images with different depths can be remarkably improved.

The invention discloses a tumor evolution trajectory prediction method and system based on image feature learning, and the method comprises the steps: obtaining the whole-process pathological section image data of a target type tumor patient, carrying out the analysis and screening of the image quality, constructing a pathological section screening strategy, and extracting a standard image; extracting tumor cell characteristics based on the standard image, performing grouping analysis on the cell characteristics of different time periods through a clustering algorithm, and determining tumor cell development characteristics; further constructing the cell development characteristics of multiple patients into a heterogeneity propagation network, simulating the tumor evolution process by using a random walk algorithm, and identifying the multi-branch evolution trajectory of the tumor; and finally, establishing a tumor evolution trajectory prediction model to predict the tumor development trend of the current patient. According to the method, the accuracy and interpretability of tumor evolution trajectory modeling can be improved, and reliable support is provided for clinical individualized diagnosis and treatment.

The invention discloses a cervical lesion intercellular relation modeling and analysis system based on a graph neural network, and the system comprises a medical image collection module which is used for collecting a digital image of a cervical tissue pathological section or a cervical TCT slide; the cell detection and segmentation module is used for extracting spatial position information and morphological characteristics of cells; the cell feature extraction module is used for extracting and fusing the spatial position, morphology, texture and biological marker features of the cells; the cell relation graph construction module is used for constructing a heterogeneous cell relation graph with cells as nodes and inter-cell relations as edges; the graph neural network analysis module is used for carrying out feature learning and modeling on the heterogeneous cell relation graph; the intelligent auxiliary diagnosis module is used for generating auxiliary diagnosis suggestions; and the data management and automatic control module is used for realizing automatic control and case data management of the whole process of the data. The intelligent and automatic level of cervical lesion cell analysis can be comprehensively improved, and the accuracy and efficiency of diagnosis are improved.

Generating polygon meshes approximating surfaces with sub-cell features. In some implementations, a computer-implemented method includes obtaining a signed distance field (SDF) grid that includes a plurality of cells, the cells including cell values that indicate distances of the cells to a surface that distinguishes an inside and an outside of an object. A boundary mesh is determined having boundary vertices and boundary faces of particular cells in the SDF grid that are based at least on cells within a threshold distance of the surface. Offset cell positions are determined for centers of neighboring cells that neighbor the boundary mesh. The offset cell positions are based on corner gradients of the neighboring cells. An adjusted mesh is generated that approximates the surface, the adjusted mesh defined by mesh vertices that are based on the boundary vertices of the boundary mesh that are displaced based on the offset cell positions.

The invention provides a cell detection map generation method based on deep learning, electronic equipment and a program product. The method comprises the following steps: acquiring a cell image, wherein the cell image comprises an image area corresponding to at least one cell; the cell image is input into a pre-established multi-modal heterogeneous network model based on deep learning, fusion features output by the multi-modal heterogeneous network model are obtained, and the multi-modal heterogeneous network model comprises a first branch unit, a second branch unit and a feature cross attention unit; updating the fusion features based on a pre-established dynamic transfer learning module to obtain updated fusion features; based on a pre-established cell feature decoupling module, decoupling the cell image to obtain a decoupling feature; and generating a cell map based on the updated fusion features and decoupling features. Therefore, the marking dependence is reduced, the artifact interference in the cell map is reduced, and the accuracy and interpretability of the cell map are improved.

The invention discloses a fault diagnosis method for a series energy storage lithium battery pack under a charging condition, and the method comprises the following steps: (1), monitoring and collecting the single voltage and temperature of each cell in real time, and uploading the single voltage and temperature; (2) taking the single voltage of the battery cell as the characteristic of the battery cell and expanding; (3) expanding the characteristics of the battery cells, and introducing a voltage correlation coefficient between the battery cells as a new characteristic dimension; (4) calculating a correlation coefficient change rate of the current time window and the previous time window as a new feature; (5) calculating a Z-Score score of the information entropy as an expansion feature; (6) determining the characteristic vectors of the single cells to obtain a final characteristic matrix; (7) the feature matrix is put into an isolated forest algorithm for abnormal point identification; and (8) further analyzing and screening the battery cell data points marked as abnormal, and determining an abnormal reason and a fault type. The method does not need battery modeling, is suitable for various different types of battery cells, and is simple, convenient and rapid.

The invention relates to the technical field of medical image processing, and discloses a tumor cell accurate recognition and analysis system based on a digital pathological image, which effectively overcomes the problem of global context deficiency caused by traditional pathological image blocking processing by constructing a microcosmic and macroscopic parallel multi-scale feature extraction mechanism. A cell topological graph is constructed by utilizing spatial semantic double constraints to simulate a biological spatial distribution rule of tumor cells, and precise navigation and weighted enhancement of microscopic cell characteristics by macroscopic organization structure information are realized through a cross-scale attention aggregation technology. Therefore, the model can fully refer to the surrounding microenvironment when identifying the heterotypic cells, and the misjudgment risk caused by background noise or local form similarity is remarkably reduced; in addition, a structured decision-making mechanism based on manifold consistency eliminates isolated prediction noisy points and ensures the continuity and rationality of a diagnosis result on a biological structure.

The present disclosure provides an attention-based MIL model for use in extracting and characterising cell features, at both the cell level and the population level. To characterise cells, cells in a well are initially fed into the model. The cells in a well include a points cloud of cells and a point cloud of corresponding cell nuclei. The cells in the well are passed through a pretrained DFN encoder which extrapolates the cell and nuclei features from the cells in the well. These extracted features are then passed through a transformer based encoder to produced transformed versions of the extracted cell and nuclei features. These transformed features are then fed into at least two classifiers. One of the classifiers is a cell-level MLP classifier which is used to compare the cell features with known drug response to attempt to match a phenotype signature with a known drug response. One other classifier is the bag classifier which is used to compare the cell population features with that of known drug responses, again to attempt to match to a phenotype signature. The outputs of the cell classification and the bag classification are used to label the cells in the well with a drug label or a potential drug label / use case.

In the blood spherical red blood cell parameter, the detection method and the identification AI training method thereof, a blood sample is preprocessed to obtain a microscopic examination sample, and the microscopic examination sample is tiled; a tiled microscopic examination sample image is shot, normal red blood cells and spherical red blood cells are recognized and labeled, labeled pictures are obtained and subjected to AI training, and an obtained AI feature data set A comprises normal red blood cell features and an obtained AI feature data set A comprises spherical red blood cell features. Identifying the microscopic examination sample image by using an AI identification algorithm, identifying spherical red blood cells in the blood sample in a selected area S1 of the image, and obtaining the total number NUMS1 of the spherical red blood cells in the blood sample in the selected image; the AI recognition algorithm recognizes the spherical red blood cells in the blood sample according to the feature data set including the spherical red blood cells. The AI training data collection efficiency is improved through diversified means, and the AI evolution efficiency is improved. Spherical red blood cell recognition is completed through advanced AI computing power, analysis is more efficient, and accuracy is higher.

The application relates to an integrated circuit technology field, and discloses a delay prediction method and a computer readable storage medium. The method comprises the following steps: obtaining a to-be-calibrated circuit, and converting the to-be-calibrated circuit into graph structure data; calculating the to-be-calibrated circuit by using a timing analysis tool to determine a to-be-calibrated delay of the to-be-calibrated circuit; encoding the graph structure data corresponding to the to-be-calibrated circuit to determine a cell feature vector, a node feature matrix and an edge feature matrix; fusing the node feature matrix and the edge feature matrix by using a feature extraction model to obtain a fused node feature matrix; aggregating the fused node feature matrix to obtain a graph-level feature vector; integrating the cell feature vector and the graph-level feature vector to determine a context feature vector; splicing the context feature vector and the to-be-calibrated delay to determine a combined feature vector; performing residual prediction on the combined feature vector, and correcting the to-be-calibrated delay based on the predicted residual to obtain a calibrated delay.

An information processing device executes processing of detecting a differential expressed gene that exhibits a specific expression with respect to a cell characteristic of interest, based on gene expression level data of a cell population in which a plurality of subtypes are mixed, and the information processing device includes a processor in which the processor assigns a cluster to which each sample of two groups obtained by dividing the cell population in accordance with the cell characteristic of interest is estimated to belong in a distribution of gene expression levels, to each sample, for each of a plurality of candidate genes that are candidates for the differential expressed gene, and searches for a first probability distribution that fits the distributions of the gene expression levels of the two groups for each of the plurality of candidate genes, based on an assignment result of the clusters.

The application relates to a kind of mitochondria-based single cell feature extraction and analysis method and system, comprising: obtaining the multiple modal images such as bright field image, nucleus fluorescent image and mitochondria fluorescent image of single cell;Image preprocessing is carried out to the three modal images obtained;For different structures such as mitochondria, morphological and texture features are extracted, and feature analysis is carried out;Further, through the fusion of mitochondria and machine learning technology, the automatic classification of cells is realized.The application is used for the classification of human cervical epithelial cells (H8) and cervical cancer cells (HeLa), and the machine learning analysis of morphological features and texture features shows the potential of mitochondria in the classification of cervical cells.The application has strong applicability, can be combined with machine learning and other analysis methods, and can be applied to various biological cells, has universality, and is easy to popularize.

Methods, systems, and devices for wireless communication are described that provide for cell selection or reselection at a user equipment (UE) based on cell selection preference criteria of the UE. The UE may receive a set of cell selection criteria that provides a priority order for cell selection based on one or more cell features, cell types, or combinations thereof. The UE, based on one or more signal measurements of available cells and the cell selection criteria, may select one of the available cells for communications. The UE may also maintain a feature cell database in which a number of cells and an associated feature mask may be stored and used to identify cells having features or types associated with the cell selection criteria for use in cell prioritization. Cell selection criteria may be used for cell selection / reselection procedures, mobility procedures, or any combinations thereof.

The invention relates to the technical field of image recognition, and particularly discloses an auxiliary blood tumor pathological diagnosis system and method based on artificial intelligence, and the system extracts a pathological image group of a patient through a pathological diagnosis auxiliary platform, analyzes the data of each pathological image, and judges the effective feature value of each pathological image; the effective feature values of the pathological images are compared with a predefined effective feature threshold value to obtain a comparison result, and the pathological diagnosis auxiliary platform judges whether the effective features of the pathological images are enhanced or not based on the comparison result; and extracting cell characteristic data in each pathological image according to each pathological image, judging the characteristic complexity of each pathological image, and performing difference analysis on the pathological image group to complete auxiliary blood tumor pathological diagnosis.

The application discloses a kind of training of cell feature extraction model, cell feature extraction method and device, belong to biological technology field.Method includes: obtaining reference cell graph, the node of reference cell graph is characterized the material group data of sample cell, the edge of reference cell graph is characterized the correlation of the sample cell corresponding to both ends node;Data enhancement is carried out to reference cell graph to obtain first cell graph and second cell graph;The first feature of each sample cell, second feature is obtained by neural network model to first cell graph, second cell graph is carried out feature extraction;Based on the first feature and second feature of each sample cell, neural network model is trained to obtain cell feature extraction model.Because the accuracy of the first feature and second feature of sample cell is higher, and eliminate noise to a certain extent, therefore, the cell feature extraction model obtained based on the first feature and second feature of sample cell can extract accurate cell feature, and have certain anti-noise performance.

The invention provides a reverse design method of an energy absorption lattice structure based on a genetic algorithm, and belongs to the field of energy absorption lattice structure optimizing.The method comprises the steps that the angle range and the distance range of a unit cell are determined; according to the angle range and the distance range, the angle parameters and the distance parameters are combined, and a unit cell set composed of a plurality of unit cells is obtained; simulating each unit cell in the unit cell set to obtain unit cell feature data; updating the unit cell set according to the unit cell feature data corresponding to each unit cell; determining target feature data according to the updated unit cell set; and according to the target feature data, constructing an energy absorption lattice structure. According to the scheme provided by the invention, the quasi-static compression finite element simulation is carried out to obtain the stress-strain curve of the energy-absorbing lattice structure, and the angle and distance of the unit cells in the energy-absorbing lattice structure are optimized based on the genetic algorithm by taking a larger platform stress value and densified strain as optimization targets; the structural energy absorption capacity of the energy absorption lattice structure can be improved.

An example method for characterizing and evaluating cells within images includes identifying, using machine-learning logic executed on a processor that is trained using cell image training data including digital microscopy images labeled with cell features, one or more cells in an image from a digital microscopy system, dividing an area of the image including the one or more cells into distinct regions to generate measurements of pixel value changes between the distinct regions, determining a presence and a location of RNA within the one or more cells in the image based on the measurements of pixel value changes, and categorizing, using the machine-learning logic executed on the processor, the one or more cells in the image when the presence and the location of the RNA is determined within the image of the one or more cells.

The invention discloses a spatial omics cell type annotation method and device and a medium, and belongs to the technical field of biological information. The method comprises the following steps: splitting unicellular omics data with cell type annotations according to cell types, clustering cells of the same cell type and generating meta-cells, and obtaining a meta-cell characteristic counting matrix; calculating specific mark characteristics of each cell type relative to other cell types; and calculating a basis matrix of each cell type mark feature, calculating a cell type weight value corresponding to each spatial position based on the feature counting matrix of the spatial omics data to be annotated, and taking the cell type with the highest weight value as the cell type annotation of the spatial position. By utilizing the method, the equipment or the medium to carry out space cell type annotation, the calculation amount in the analysis process is greatly reduced, the analysis efficiency is improved, and the accuracy and the stability of annotation are improved.

Example systems, methods, and non-transitory computer readable media are directed to obtaining a point cloud that represents an environment based at least in part on a plurality of points in three-dimensional space; determining corresponding classifications of points in the point cloud as ground or not-ground based at least in part on a plurality of ground classification algorithms; determining respective point cloud features associated with the points in the point cloud; determining respective cell features associated with a plurality of cells that segment the point cloud; generating feature data for a machine learning model based at least in part on one or more of: the classifications of the points based on the plurality of ground classification algorithms, the point cloud features, or the cell features; and classifying the points in the point cloud based at least in part on an output from the machine learning model.

The application belongs to the technical field of single cell RNA sequencing, and particularly relates to a single cell RNA sequencing data interpolation method based on robust non-negative matrix factorization. The single cell RNA sequencing data interpolation method based on robust non-negative matrix factorization obtains optimal parameters of a cell feature matrix W and a gene feature matrix H by using a target function of a scRNA-seq data interpolation method based on robust non-negative matrix factorization, and then predicts the interpolated cell gene expression data by using a scRNMF model. The target function includes two loss functions, namely a C-loss loss function and a least square loss function. The scRNA-seq data interpolation method based on robust non-negative matrix factorization is hereinafter referred to as scRNMF. The method provided in the application solves the target function by training, determines the scRNMF model by using the solving result, and predicts the result by using the determined scRNMF model.

The present application relates to the field of image processing technology, and proposes a textual annotation method, device, electronic device, and computer program product for cell images. The method comprises: obtaining a cell image to be processed; extracting pixel-level cell feature information from the cell image; and generating fine-grained description text of the cell image based on the cell feature information. Since the above-mentioned fine-grained description text is generated based on pixel-level cell feature information, it describes in detail the spatial position and statistical distribution of each cell in the cell image, and thus can help the large language model understand the semantic relationship and spatial connection between local regions in the cell image, thereby obtaining in-depth and detailed cell image analysis and inference results.

The construction method of the digital cell basic model disclosed by the invention comprises the following steps: inputting single cell transcription sequencing data and related biological characteristics, and respectively encoding and integrating the data into node characteristics and edge characteristics of a cell map; inputting the formed cell graph into GNN, and adopting a message passing mechanism to jointly learn feature representation of nodes and edges; learning a global relationship among genes in the cell map through an attention mechanism, and outputting feature representation of the genes; and coding based on the feature representation of the gene to obtain a cell feature vector. According to the digital cell basic model CGCompass provided by the invention, pre-training is carried out on five million pieces of human single cell sequencing data, so that information of biological significance of genes and information of interaction between the genes can be learned; biological cell downstream tasks such as cell clustering, cell classification, single-gene disturbance prediction and bulk gene knockout prediction can be effectively completed through two modes of fine tuning and zero sample reasoning.

The invention particularly relates to the technical field of stem cell preparation and tissue engineering, and discloses a placenta mesenchymal stem cell multi-source extraction system based on an integrated treatment platform. Comprising a multi-region synchronous pretreatment module, a zoning adherent culture module, a differentiated cell harvesting module, a cell characteristic collection module, a functional cell division module and a whole-process closed-loop control module, the multi-region synchronous pretreatment module adopts an integrated design, and the zoning adherent culture module realizes centralized culture through an independent marking region; the differentiation cell harvesting module is used for carrying out merging amplification; the cell characteristic acquisition module is used for acquiring cell characteristic data; the functional cell division module is used for realizing cell type and function judgment; the whole-process closed-loop control module is used for realizing whole-process quality tracing; through the integrated design, the cost is reduced, the cell quality stability is ensured, and the whole-process quality tracing is realized.

This invention discloses a cross-modal cell alignment method for pathological images in non-registerable scenarios. The method acquires H&E and mIF stained images and their data-augmented views corresponding to spatial anatomical locations; constructs H&E modality processing branches, mIF modality processing branches, and a reverse self-attention module; and sequentially performs three-stage progressive training: intra-modal contrastive pre-training based on the data-augmented view; using mIF modality-level semantic aggregation tokens from the same spatial anatomical location as positive samples and mIF modality-level semantic aggregation tokens from different spatial anatomical locations as negative samples, achieving H&E to mIF modality-level semantic alignment through contrastive learning; inputting the aligned H&E modality-level semantic aggregation tokens and the projected H&E cell feature embedding set into the reverse self-attention module, and achieving unsupervised cell-level semantic alignment by minimizing the Hungarian matching loss; finally, the output H&E cell features semantically aligned with mIF are embedded into a refined set, which can be directly used for downstream pathological analysis tasks such as high-precision cell clustering.

The invention discloses a training method of a cell classification model and a cell classification method and device, and belongs to the technical field of computers. The method comprises the following steps: acquiring a plurality of sample data sets, wherein one sample data set comprises a plurality of sample cell data; based on prediction classification information and annotation classification information of one sample cell data, first loss of the sample cell data is determined, and the prediction classification information is obtained by extracting sample cell characteristics of the sample cell data through a neural network model and classifying the sample cell characteristics; determining a second loss of the pair of sample data sets based on each sample cell feature of one sample data set and each sample cell feature of the other sample data set; and training a neural network model based on each first loss and each second loss to obtain a cell classification model. The model is trained through the first loss and the second loss, the batch effect between the sample data sets is eliminated, the accuracy of the model is improved, and therefore the accuracy of the classification result is improved.

The present application relates to a kind of pathological image cell population feature extraction method and system, wherein the method comprises the following steps: obtaining pathological image;Pathological image is input into cell nucleus segmentation model, and cell nucleus segmentation result is obtained;Pathological image is cropped based on cell nucleus segmentation result, and the cell image of each cell in pathological image is obtained;Cell image is input into the cell feature extraction model based on contrast learning, and the feature and cell location information of each cell are obtained;The feature set of all cells and corresponding cell location information are input into the population feature extraction model based on contrast learning, and the cell population feature is obtained, wherein, population feature extraction model generates positive sample of contrast learning by randomly selecting rectangular region of different size, arbitrary rotation angle in pathological image during training process.Compared with prior art, the present application has the advantages of good robustness, strong generalization ability and strong explainability.

The single cell identification described herein utilizes cell image information and extracts cell features with a neural network model to subtly distinguish the noise events from single cells, allowing the user to choose which different types of noise events to exclude depending on the requirement of applications. The fast neural network model is able to extract more abundant and specific cell features than handpicked features, which enables the model to be equipped with higher accuracy and higher discriminative capability of distinguishing noise events and identifying the single cells in real-time. Utilization of a neural network model for real-time single cell identification represents a novel technique never applied before. It allows high discriminative capability and high accuracy compared to traditional FACS (Fluorescence-activated Cell Sorting). The usefulness of this technique is to integrate with any brightfield (BF) model and fluorescence (FL) model to identify single cells for different downstream applications.

The systems and methods described herein relate to performing one or more highly multiplexed cell assays. In some embodiments, one or more channels of a fluidic device are provided with a photopolymerizable polymer precursor and cells randomly arranged on a surface, followed by measurement of cell position by a detector, synthesis of a hydrogel chamber via photopolymerization to encapsulate individual cells, and loading of assay reagents into the channels. An assay signal indicating the desired cellular characteristics is generated for each of the encapsulated cells.

The present application relates to a single-cell protein subcellular localization model based on weakly supervised multi-instance learning, and relates to the technical field of biological information. The model comprises a cell feature extractor, an image branch, a cell branch and a class-aware adaptive pruning module. The cell feature extractor is used to encode single-cell images into single-cell feature vectors. An image-level classifier in the image branch is used to output an image-level protein subcellular localization prediction result according to the image-level feature representation. A cell-level classifier in the cell branch is used to output a single-cell-level protein subcellular localization prediction result according to the single-cell feature vector. The class-aware adaptive pruning module generates single-cell pseudo labels through several label sources. The model of the present application can solve the problems of cell label noise and class long-tail distribution under weak supervision, thereby realizing more accurate and stable single-cell localization prediction and providing a powerful tool for single-cell heterogeneity analysis.

The invention relates to a method for determining user features and classifying cancer users, a medium and equipment, and relates to the technical field of machine learning. The method comprises the steps of calculating feature importance degrees of original cell features of a target user based on a preset weight value calculation model, and sorting the original cell features based on the feature importance degrees to obtain first target cell features; constructing a first original feature map of the target user according to the first target cell feature, and inputting the first original feature map into a preset feature map processing model to obtain a first target feature vector; performing clustering processing on the target user based on the first target feature vector to obtain a first user clustering result, and determining a first contour coefficient according to the first user clustering result; and determining a target contour coefficient according to the first contour coefficient, and determining a target user feature corresponding to the target user according to the target contour coefficient. The calculation efficiency is improved.