60 results about "Cell segmentation" patented technology

The invention relates to the field of image processors and biological medicines, and discloses an NK cell activity rapid detection method based on image processing. The method comprises the following steps: acquiring an unmarked time sequence phase image sequence of an NK cell and target cell co-culture system; performing cell instance segmentation to track individual cells; extracting a morphological dynamic characteristic parameter set of the target cell, wherein the morphological dynamic characteristic parameter set comprises a volume change rate, a phase gradient entropy, a cytoplasm phase fluctuation frequency and a nuclear region phase mean value; inputting the parameters into a pre-trained death state discrimination model, and outputting a death probability; and calculating a killing efficiency index based on the death probability evolution curve, and judging the activity level of the NK cells. The system comprises a phase image acquisition unit, a cell segmentation unit, a feature extraction unit, a death judgment unit and an activity judgment unit. Through unmarked imaging and deep learning fusion analysis, high-precision, real-time, quantitative and ultra-early NK cell activity evaluation is realized, and the method is suitable for clinical instant inspection and immunotherapy monitoring.

The invention discloses a morphological feature-based cell segmentation and cell nucleus identification method for a turned unstained bone tissue pathological image. The method comprises the following steps of: 1, eliminating tool marks by adopting a tool mark elimination method combining local frequency domain analysis and directional suppression; 2, performing cell segmentation by using a K-means method, and performing morphological expansion and topological analysis on a segmented single cell image to identify a cell nucleus in the single cell image; step 3, calculating morphological characteristic indexes of each region; the method comprises the following steps: establishing a multi-dimensional Gaussian mixture model according to existing bone cell labeled sample information, performing outlier detection according to statistical data analysis, and removing results which do not conform to cell morphology; classifying different regions, and removing non-cell regions; by calculating morphological characteristic indexes of each region, different regions are distinguished according to the indexes, and cells are preliminarily screened. According to the method, high-precision cell segmentation and cell nucleus identification can be carried out on the cut undyed bone tissue pathological image.

Systems and methods for multi-modal subcellular segmentation using photolysable biomarkers and / or transcriptomic readout density maps are disclosed. The systems and methods improve the accuracy of cell segmentation of the nucleus, cytoplasm, and cell membrane regions by using optical and bleach correction from a variety of photolysable morphological markers in combination with high quality 3D images acquired with high dynamic range scans and spatial transcriptomic readout density maps.

The invention discloses a multispectral microscope blood cell automatic classification and counting system. The system is composed of a multispectral illumination and microscopic imaging module, a spectrum and geometric calibration module, a multispectral preprocessing and cell segmentation module, a multispectral discrimination index and spectral band weight adaptive updating module, a cell graph structure classification module, a man-machine interaction module, an online adaptive learning module and the like. The method comprises the following steps: acquiring a blood smear image by a system under a narrow-band multi-spectrum condition, constructing cellular spectrum-morphological characteristics by combining a multi-scale segmentation result after noise suppression, flat field correction and background deduction, generating a discrimination index with a self-adaptive spectrum band weight, and completing joint classification and counting on a cell map; and meanwhile, carrying out constrained increment updating on the spectral band weight and the classification model by utilizing an artificial correction result of the low-confidence-coefficient cells. Compared with a traditional single-channel microscopic imaging and static classification method, the method has higher classification accuracy and counting stability under different dyeing and imaging conditions, and the workload of manual recheck can be reduced.

This invention provides a method and system for macrophage morphology recognition that integrates multimodal data. The method includes acquiring a time-lapse imaging sequence of live macrophage cells; segmenting and tracking individual cells using a probabilistic model of cell contour evolution and intracellular texture flow to obtain motion trajectories and continuous morphological contour sequences; acquiring behavioral features based on the motion trajectory; obtaining morphological features based on the morphological contour sequences; calculating local field influence features based on the behavioral and morphological features of neighboring cells within a neighborhood search radius; constructing a cell interaction graph structure based on the three types of features combined with intercellular Euclidean distance, motion direction correlation, and morphological features of cells at both ends; inputting the cell interaction graph into a trained graph attention network; and determining whether each macrophage is of subtype M1 or M2 based on the output.

The invention discloses a synchronous imaging method for a multicellular structure in a multicellular type. The synchronous imaging method comprises the following steps: S1, marking the cellular structure in the multicellular type by using fluorescent protein; s2, forming a spectrum-spatial feature joint coding set according to the spectrum and spatial features; s3, performing spectral unmixing on the spectral image to obtain an abundance image of each fluorescent component; s4, performing cell segmentation and cell structure positioning, and extracting spatial features; and S5, carrying out joint decoding on the spectral features and the spatial features to distinguish different cell types, and carrying out synchronous imaging on the multi-cell structure. The method has the beneficial effects that different cell types are marked by using corresponding fluorescent proteins, and a spectrum-space coupling coding strategy is formed in combination with spatial position characteristics, so that simultaneous observation and dynamic analysis of different cell types and a plurality of internal structures in the same imaging view field are realized; and the limitation that traditional spectral imaging can only work in a single cell type is broken through.

The invention relates to a spatial analysis single cell state modeling method and system based on domain self-adaption and layered fine tuning, and the method comprises the steps: obtaining multiple immunofluorescence images and single cell segmentation masks, and constructing a no-label data set; constructing a mask auto-encoder composed of a ViT encoder and a linear decoder, adding a classification token in front of the image, carrying out field adaptive training on the mask auto-encoder based on the unlabeled data set, learning the classification token, and obtaining a field adaptive weight of the ViT encoder; obtaining a labeled data set; constructing a state embedding generation model, wherein the state embedding generation model comprises a shared ViT backbone network and a two-stage classifier; a classification token is added in front of an image feature sequence in the labeled data set, hierarchical training is carried out on the state embedding generation model, and the classification token is learned; and inputting the cell image blocks into the trained state embedding generation model, outputting a classification result and cell state embedding, and carrying out interpretability analysis. Compared with the prior art, the method has the advantages that accurate cell classification can be realized, and cell state representation with biological interpretability can be generated.

The invention provides a cell interpretation method and device based on uncertainty evaluation, and the method comprises the steps: carrying out the cell segmentation and feature extraction of a sample image of a target sample, and determining a plurality of to-be-interpreted cells in the sample image and the feature information of each to-be-interpreted cell; respectively inputting each piece of feature information into a fusion interpretation model comprising a plurality of interpretation sub-models to obtain a prediction probability value and uncertainty measurement output by each interpretation sub-model so as to predict the probability that each to-be-interpreted cell is a target cell and evaluate the uncertainty of the probability; and determining a score value of each to-be-interpreted cell by a fusion layer in the fusion interpretation model based on the prediction probability value and the uncertainty measurement, and interpreting whether each to-be-interpreted cell is a target cell based on the score value so as to determine a cell interpretation result of the target sample. Through the method, the stability, the accuracy and the efficiency of interpreting the cells are improved.

A spatial in situ sequencing method, belonging to the field of biology, is proposed. It utilizes an electric field-assisted directed migration of mRNA and in-situ capture with primers on a microarray surface to enrich tissue and release mRNA. In-situ reverse transcription generates covalently fixed cDNA, ensuring high positional stability during multiple rounds of hybridization and imaging. After reverse transcription, tissue is digested to remove tissue, reducing spatial hindrance and background interference, while the cDNA remains at its original coordinates due to covalent anchoring. Combining coding probe hybridization and RCA, single-molecule-level signal amplification and recognition are achieved. Through decoding and single-cell segmentation, transcripts are mapped to their respective cells, constructing a single-cell resolution spatial gene expression map. This method does not rely on multi-round DAPI mapping or other endogenous morphological marker-based multi-cycle image registration methods, making it suitable for high-throughput spatial in situ sequencing and significantly improving robustness and versatility in complex imaging scenarios such as thick tissue sections and low signal-to-noise ratios. It is applicable to high spatial resolution, high-throughput spatial transcriptome research.

The invention belongs to the technical field of document image processing and data mining, and particularly discloses a geoscience field literature scatter diagram data extraction method, a storage medium and equipment, and the method comprises the steps: classifying pictures extracted from geoscience field literature PDF into conventional scatter diagram pictures and table type scatter diagram pictures; positioning an independent scatter diagram region in the conventional scatter diagram picture by adopting a target detection model, segmenting the independent scatter diagram region to obtain a first type of independent scatter diagrams, extracting cells in the table type scatter diagram picture by adopting a cell segmentation method based on morphological operation and line segment intersection detection, and obtaining a second type of independent scatter diagrams; the cells are spliced with the coordinate axis area of the picture to obtain a second type of independent scatter diagrams; and inputting the first type of independent scatter diagrams and the second type of independent scatter diagrams into a scatter diagram data extraction model to obtain coordinate axis scale lines, then converting pixel coordinates of scatter points into actual data values, and outputting scatter diagram data. According to the method, the scatter diagram data can be automatically and accurately extracted from the geoscience literature.

A deep neural network-based method for detecting living cell morphology may include identifying and locating one or more living cells within an acquired image to be detected by using a deep neural network-based target detection model, so as to extract one or more living single cell images. segmenting the image of the one or more living single cells by using a deep neural network-based cell segmentation model, so as to obtain one or more feature part of the one or more living single cells. and analyzing and determining a morphological parameter of the one or more living single cells based on the one or more feature parts. Thus, the activity of the detected cells can be ensured, and a non-destructive, accurate, and rapid detection of living cell morphology can be achieved.

The present application relates to the technical field of cell image analysis and medical artificial intelligence, and discloses a cell segmentation and adaptive cascade reasoning method and system based on prior frame guidance. The method comprises: acquiring a multi-modal cell image with a detection frame; performing adaptive histogram equalization preprocessing on the image and executing global preliminary screening segmentation; calculating a multi-dimensional weighted score of the mask and the detection frame, if the score is lower than a first matching threshold, extracting a local image block to dynamically adjust a flow field threshold and an estimated diameter for cascade retry; if the score after retrying is lower than a second threshold, triggering a label consistency protection mechanism to discard or back up poor samples; finally, performing connected domain purification on the retained mask, and calculating a topological solidity, and performing convex hull reconstruction on the mask with low solidity. Through two-stage reasoning, double-track quality filtering and topological constraint, the present application effectively improves the segmentation effect of dense and irregular cells and improves the generalization performance of downstream analysis.

The present invention relates to a cell analysis system based on virtual fluorescence generation technology, and a method therefor. According to the present invention, the system comprises: an input unit that receives a quantitative phase image of a sample including at least one cell through digital holography microscopy; and a cell identification unit that identifies at least one living cell by applying, to the received quantitative phase image, a cell segmentation mask generation model and a nuclei segmentation mask generation model constructed previously, and that masks a position of the nucleus of the living cell to derive an identification result. The system may further comprise a post-processing unit that derives a final result by applying a preset post-processing method to the derived identification result.

The invention aims to provide a biological prior-based cell medical image segmentation method, which comprises the following steps of: A, constructing a neural network which comprises a coding network and a decoding network; the coding network comprises a VSS branch, a YOLO network and a GNN branch; b, inputting the original image into a decoding network, dividing the original image into two paths, and obtaining a first preprocessing result after the first path is processed by a convolutional layer and an LN function in sequence; the first preprocessing result is input into a VSS branch to be processed, and the result is input into a decoding network; in the second path, each single cell in the image is detected and obtained through YOLO network processing, the background is removed, and the background-removed image is processed through three convolutional layers in sequence to obtain a second preprocessing result; the second preprocessing result is input into a GNN branch to be processed, and the result is input into a decoding network; and C, the decoding network decodes each input result to obtain a final segmentation processing result. According to the method, the cell segmentation precision can be improved, and powerful support is provided for histological analysis and diagnosis.

This invention discloses a cell segmentation method, device, storage medium, and program product based on spatial omics sequencing. The method includes: acquiring a whole-slice image, wherein the whole-slice image indicates the distribution characteristics of spatial omics signals in the tissue slice; dividing the whole-slice image into multiple image blocks, identifying whether heterogeneous regions exist in the multiple image blocks, and obtaining identification results; preprocessing each image block according to the identification results to obtain preprocessed image data corresponding to each image block; forming the input of a deep learning segmentation model based on the preprocessed image data corresponding to each image block, and outputting the segmentation results of each image block through the deep learning segmentation model; and obtaining each cell region in the whole-slice image based on the segmentation results of each image block.

The application belongs to the technical field of image recognition segmentation, and discloses a medical image cell segmentation and tracking method, which comprises the following steps: step 1: data processing; feature extraction: the backbone part in the model is used to extract features from the preprocessed image, and the CSPDarknet structure is adopted in YOLOv8; step 3: FPN-PAN multi-scale feature fusion; step 4: Head prediction according to multi-scale features. The application realizes real-time tracking of the motion trajectory of cells by combining with a tracking algorithm such as deepsort. The method is mainly based on the YOLOv8 framework, and the Simam attention mechanism and the multi-scale proto method are adopted to optimize the model, so that the detection effect of YOLOv8 is further improved. The application can automatically complete the analysis and detection of medical images, is high in convenience and easy to use.

This invention provides a system and method for multimodal intracellular segmentation using photocleavable biomarkers and / or transcriptome read density maps. [Solution] The system and method improve cell segmentation accuracy of the nuclear, cytoplasmic, and membrane regions by using optical and bleaching corrections from multiple sources of photosectionable morphological markers, in combination with high-quality 3D images acquired by high dynamic range scanning and spatial transcriptome read density maps.

This disclosure provides a model training and cell segmentation system, method, and storage medium. The model training system includes a first processor configured to: acquire a first dataset and a self-supervised training model; augment the first dataset to obtain first augmented data and second augmented data, inputting the first augmented data into a first encoder to obtain first positive sample features, and inputting the second augmented data into a second encoder to obtain second positive sample features; inputting the first positive sample features, the second positive sample features, and negative sample features constructed based on the second positive sample features into a contrastive learning module to obtain a contrastive learning result; and adjusting the model parameters of the self-supervised training model based on the contrastive learning result to obtain a feature extraction model, wherein the feature extraction model is used to implement the segmentation process of at least two cells. The technical solution of this disclosure can accurately segment cells.

The invention relates to the technical field of medical image pathology analysis, in particular to a pathology image cell segmentation method and device based on a large model and knowledge distillation, and the method comprises the steps: generating a to-be-segmented image through employing a target slice image; generating a target prompt feature vector based on a target prompt encoder; extracting a first image feature of the to-be-segmented image by using a first target image encoder, and determining a second target image encoder based on a knowledge distillation technology to extract a second image feature of the to-be-segmented image; and inputting the target prompt feature vector, the first image feature and the second image feature into a target mask decoder to obtain a preliminary cell segmentation mask, performing feature fusion to obtain an enhanced cell segmentation mask, and further determining a cell segmentation result of the to-be-segmented image. Therefore, the problems that the model training time is increased, the calculation burden is increased, the cell boundary cannot be accurately described, and the accuracy and robustness of cell segmentation are reduced in a cell segmentation method in the related technology are solved.

Methods for the image processing of cells are disclosed for the purpose of segmenting cell colonies for further processing to determine confluence, counting and morphology.

The application discloses a low-cost universal virtual phase contrast method and device based on a cylindrical lens; the method comprises the following steps: adding a cylindrical lens in a common bright field microscope of a Kohler illumination structure, so that the illumination light source forms asymmetric illumination, and a bright field image is obtained; a strong image carries more phase information; the obtained bright field image is input into a conditional generative adversarial neural network under credibility negative feedback after training, and a virtual phase contrast image is generated, so that the effect equivalent to a standard phase contrast image is realized at low cost. The application not only realizes the effect similar to the standard phase contrast microscope at low cost, but also is superior to the image of the standard phase contrast microscope in some applications (cell segmentation, cell recognition, etc.), and expands the application potential of the application in the fields of biomedicine, material science and the like.

The application relates to the technical field of medical image processing, and particularly discloses a cervical cancer screening pathological large model construction method based on DINOv3-TCT. The technical problem to be solved by the application is that when a general visual Transformer model is directly applied to a cervical cell instance segmentation task, there are problems of mismatch between model internal feature representation and instantiation target and high calculation redundancy. Therefore, the application proposes to transform the DINOv3 encoder: inject a learnable query token at a specific layer, and innovatively construct an instance decoupling loss term acting on an attention weight matrix to explicitly guide the encoder to realize instance-level feature separation during training. The method optimizes the internal attention distribution of the model, improves the accuracy of dense cell segmentation, and simultaneously reduces the model parameter quantity and calculation overhead through integrated design, so that the balance between high accuracy and high efficiency is realized.

This invention relates to a method and apparatus for bright-field cell image segmentation in fluorescence microscopy. Combining an improved two-dimensional OTSU threshold segmentation algorithm, it filters out noise points in single-cell images during image preprocessing and further refines cell segmentation using binary image mathematical morphology. Then, it segments adhered cells using a label-controlled watershed segmentation algorithm based on cell nucleus images. This invention improves segmentation results through image enhancement and refines them using various segmentation methods, effectively addressing issues such as weak edges, poor contrast, irregular cell shapes, and cell adhesion in bright-field cell images. Therefore, the overall visual segmentation effect is quite good.

The invention discloses a Citrus chachiensis oil sac grading method and system based on a YOLO-LEC model. The method comprises the following steps: an image acquisition step: acquiring image data of Citrus chachiensis epidermis by using an image acquisition workbench system; a data processing step: marking and enhancing the acquired image data, and dividing the acquired image data into a training set and a verification set; a grading standard step: formulating the grading standard of the Citrus chachiensis oil cells based on the oil cell area and the oil cell density, and dividing the Citrus chachiensis into a plurality of grades; a model construction step: constructing a YOLO-LEC segmentation model, wherein the YOLO-LEC segmentation model is based on a YOLOv12-seg model; a model training step: training the YOLO-LEC segmentation model by using the training set, and performing verification and performance evaluation on the training process by using the verification set to obtain an optimal oil cell segmentation model; and a segmentation and classification step: segmenting the Citrus chachiensis oil cells by using the optimal oil cell segmentation model. According to the invention, automatic, standardized and high-precision grading of the Citrus chachiensis oil sacs can be realized.

The application relates to the technical field of medical image segmentation, and discloses a semi-supervised lymphoma cell segmentation system and method based on pseudo label screening, proposes small block patch cutting of different resolutions, realizes multi-scale instance feature and image feature collaborative representation through multi-scale deep feature extraction and fusion of an EfficientNets model, introduces a trained XGBoost model as an accurate quality filter, carries out uncertainty, fixed threshold and adaptive threshold screening on the preliminary results of an LC-YOLO model, the adaptive threshold screening of the XGBoost model can dynamically judge the authenticity of each predicted target according to the fusion features of the predicted target, effectively eliminates noise prediction inconsistent with the features of real cells, and ensures the reliability and stability of the final high-quality pseudo label.

The invention discloses a cell segmentation method based on multi-channel fluorescence feature fusion, and relates to the technical field of cell segmentation. Comprising the following steps of data preprocessing and channel synchronization, network architecture design, cell nucleus positioning, mask generation and the like. Through a deep learning technology and in combination with multi-channel image data such as DAPI and SpGreen, accurate automatic segmentation of cell nucleus and cytoplasm regions is realized, challenges of intercellular adhesion and overlapping are effectively solved through introduction of an attention mechanism and multi-scale feature fusion, meanwhile, cell boundaries are optimized through distance transformation and a conditional random field CRF, the segmentation precision is improved, and the segmentation efficiency is improved. The subsequent cell counting and co-expression analysis function enables a user to accurately evaluate cell distribution and co-expression conditions of different fluorescence channels, and a segmentation result and a data visualization report provided by the method provide an efficient and accurate analysis tool for cell biology research, and promote automation and refinement of cell image analysis.

The embodiment of the invention provides a method and system for automatically assisting lymphoma pathological cell labeling and training, and belongs to the technical field of medical image labeling. The method for automatically assisting lymphoma pathological cell labeling and training comprises the following steps: acquiring a lymphoma pathological cell image uploaded by a user, and separating a cell part in the lymphoma pathological cell image through an SAM model; and identifying the features of the cell part through a ViT model, completing classification, and generating a cell labeling classification result. According to the method for automatically assisting in lymphoma pathological cell labeling and training, organic combination of an automatic labeling technology and a collaborative labeling mechanism is achieved, efficient automatic labeling is supported, manual participation in adjustment and confirmation is allowed, and the efficiency and quality of pathological image labeling are remarkably improved through multiple rounds of collaboration and intelligent aggregation. According to the method, the cell segmentation model can be automatically optimized, and the revised result of manual annotation is used as new training data to optimize model parameters. The system not only can be used as a marking tool, but also can be used as a training and skill growth tool for green doctors.

The invention discloses a bone marrow cell morphology identification method and system based on a cross-domain adaptive joint convolutional neural network, and relates to the technical field of computer-aided diagnosis, the method comprises the following steps: S1, obtaining bone marrow cell image data, and carrying out image segmentation through a dual-path mask optimization segmentation module to obtain a single cell segmentation image; s2, extracting and fusing pathological features of the single cell segmentation image through a four-dimensional feature fusion module to obtain a spatial fusion feature vector; s3, performing feature alignment on the spatial fusion feature vector through a cross-domain adaptive joint module to obtain an aligned domain invariant feature vector; and S4, outputting a cellular morphology recognition type from the multi-center feature distribution vector through a dynamic element classifier. According to the method, high-precision and high-robustness automatic recognition of the bone marrow cellular morphology in a high inter-domain difference environment is realized, and the method has a significant clinical application value.

The one or more embodiments of the specification provide a sample image analysis system, method and related model training method. The sample image analysis system and method measure the similarity between two cell segmentation images to be matched by performing image segmentation on the image captured based on a high-power objective lens, extracting features of the two cell segmentation images to be matched based on a trained cell feature extraction model, and then calculating the vector similarity of the two cell feature vectors extracted to measure the similarity between the two cell segmentation images to be matched, serving as the basis for deduplication, which can improve the cell image deduplication accuracy, improve the accuracy of related cell counting, and improve the reliability of the sample image analysis system. In addition, the training method of the above-mentioned cell feature extraction model can make the trained cell feature extraction model have better cell feature extraction performance by performing data enhancement processing on the sample cell image and taking the obtained enhanced image as the positive training sample of the sample cell image.

The application relates to a visual attention-based unsupervised cervical cell instance segmentation method, and relates to the problems of missing labeled data and accurate segmentation of cervical cells in intelligent auxiliary diagnosis technology of cervical cancer. Computer intelligent auxiliary diagnosis technology is widely applied, and cell segmentation technology is the basis of various downstream tasks. A deep learning model needs a large amount of labeled data for training, pixel-level labeling is time-consuming and labor-consuming, and there are impurities such as bacteria, white blood cells and bubbles caused by physiological reasons and film reasons, in addition, there are problems such as overlapping adhesion and visual inseparability of cervical cell images. In order to improve these problems, a visual attention-based unsupervised cervical cell instance segmentation method is provided. Experiments show that the method can effectively improve the accuracy of segmentation and reduce the missing detection problems caused by the interference of impurities and incomplete labels. The application is applied to accurate segmentation of cervical cells under the condition of no label.