17 results about "Complex cell" patented technology

The invention belongs to the field of bioinformatics, and relates to an improved integrated deep learning cell communication ligand-receptor interaction prediction method. The method comprises the following steps: firstly, carrying out extraction and dimensionality reduction on biological sequence features of a ligand and a receptor, and constructing multi-modal feature input; secondly, constructing an improved deep neural network branch, introducing a batch normalization layer and a Leaky ReLU activation function, solving the problems of gradient disappearance and neuronal necrosis, and improving regularization strength to prevent overfitting; meanwhile, an enhanced heterogeneous graph auto-encoder branch is constructed, the graph embedding dimension is remarkably expanded to improve the feature capacity, and full convergence of the model is ensured by increasing training rounds; thirdly, fusing the improved deep network with the prediction probability of a heterogeneous graph auto-encoder by adopting a weighted integration strategy; and finally, outputting a potential interaction relationship based on the fusion probability. By optimizing the architecture and the strategy, the prediction accuracy and robustness are remarkably improved, and a reliable tool is provided for analyzing a complex cell communication network.

The invention discloses composite hydrogel bio-ink with a function of space-time delivery of double growth factors as well as a preparation method and application of the composite hydrogel bio-ink, and belongs to the technical field of biomedical materials and tissue engineering. According to the preparation method, imidazolyl-modified methacrylated gelatin and double-bonded PF127 are compounded, and meanwhile, free vascular endothelial growth factors and connective tissue growth factor-loaded PLGA microspheres are entrapped in a system, so that the bio-ink with excellent printability, high adhesion, swelling resistance and space-time delivery function is formed; the bio-ink physically has the advantages of high printing fidelity, low swelling property, high mechanical strength and strong tissue adhesion of a synthetic material; in biology, the system can be used as an intelligent carrier to realize programmed space-time delivery of various growth factors, so that complex cell biological behaviors are accurately arranged, and real regeneration of functional tissues is guided.

This invention discloses a cervical cell classification method based on an attention mechanism and the Swing Transformer, belonging to the field of medical image processing technology. This invention proposes a CFA-Former network model based on a CFA module. By combining channel attention and spatial attention, it overcomes the limitations of traditional models in capturing multi-scale features. Furthermore, by strengthening the focus on important information and location, this model effectively improves the accuracy and robustness of cervical cell classification tasks. In the model design, the CFA module adaptively focuses on and suppresses important features through two learning paths, comprising two sub-modules: CDA and SFA. The CDA module optimizes information extraction in the channel dimension through a lightweight channel attention mechanism, while the SFA module enhances the model's feature representation ability in the spatial dimension through a strengthened spatial attention mechanism, demonstrating significant advantages, especially when dealing with complex cell images.

The invention discloses a lipid droplet automatic segmentation and quantitative analysis method based on deep learning, and relates to the technical field of cytobiology, and the method comprises the steps: carrying out the preprocessing of an input cell image, and carrying out the normalization of a pixel value to a preset value interval through the image standardization operation; inputting the preprocessed image into an improved UNet segmentation model, and outputting a pixel-level segmentation mask of a lipid droplet area through an encoder and decoder structure in the model in combination with a jump connection and attention mechanism; performing morphological post-processing on the lipid droplet segmentation mask to obtain an optimized lipid droplet segmentation result; extracting geometric features of each lipid droplet based on the optimized lipid droplet segmentation result, and calculating one or more lipid droplet quantitative indexes according to the geometric features; and generating and outputting data containing the lipid droplet segmentation result and the lipid droplet quantitative index. The method can adaptively focus on the lipid droplet area in the image, effectively inhibits the interference of a complex cell background, and guarantees the segmentation accuracy.

The invention belongs to the technical field of cell biology, and particularly relates to a triple co-culture cell model for respiratory function research as well as a construction method and application of the triple co-culture cell model. Based on BEAS-2B, THP-1 and MRC-5 cells, a triple co-culture cell model is constructed by adopting a Transwell three-dimensional construction mode, and a complex cell interaction environment after human respiratory tract tissues are exposed to harmful factors such as heavy metals and the like can be simulated. The constructed model is closer to a real physiological anatomical structure in structure, and the multicellular synergistic toxic reaction caused by heavy metal exposure is more comprehensively reproduced in a functional level; an integrated in-vitro model which is closer to human lung tissue in structure, covers multi-stage reaction in function, is standard and stable in operation and has multi-dimensional analysis capability in mechanism is realized for the first time, scientificity, sensitivity and practical applicability of research on respiratory system toxicity caused by heavy metal are remarkably improved, and the method has relatively high technical advancement and industrial transformation potential.

The invention discloses a micromolecular fluorescent probe for specific imaging autophagy and a preparation method and application thereof, the fluorescent probe comprises a fluorophore, a linking group and an autophagy targeting group, the fluorophore is an intelligent fluorescence reporter group, the linking group adopts cysteine as a linking unit, and the autophagy targeting group targets LC3 protein; the probe can be used for specifically imaging an autophagy process of a biological sample and screening an autophagy regulator. The micromolecular fluorescent probe has the advantages of being good in cell membrane permeability, simple and convenient in dyeing process and easy to be compatible with other fluorescence labeling technologies, can perform specific recognition and selective imaging on an autophagy related structure, improves the targeting property and imaging credibility of the probe in a complex cell environment, and can be used for detecting autophagy related structures. The method can be used for visual tracing and detection of autophagy flow in living cells under physiological and pathological conditions, and is beneficial for promoting a small-molecule fluorescent probe to analyze an autophagy regulation mechanism and biological functions in real time.

The application provides a method for synchronously detecting multiple cell death modes in a tissue slice based on multiplex immunofluorescence, and belongs to the technical field of biological detection. The application realizes the synchronous labeling and visualization of multiple cell death modes in a single tissue slice, significantly improves the detection efficiency and saves precious samples; by integrating key biomarkers covering main cell death modes in the same detection system, a self-defined interpretation scheme based on multi-marker expression combination is constructed, effectively reducing the error caused by non-specific expression of a single marker, improving the reliability and rationality of the death mode classification, and providing a general solution for rapid screening of complex cell death networks. The application is suitable for anticancer drug efficacy evaluation, combination drug regimen screening and disease mechanism research, and has important scientific research value and clinical conversion prospect.

The invention discloses a retinoic acid X receptor alpha activation effect molecule detection method based on a fluorescence polarization technology, and belongs to the technical field of biological analysis. According to the method, the change of a probe fluorescence polarization signal caused by the change of the binding state of the RXR alpha and the fluorescent nuclear receptor co-regulatory peptide is directly monitored, so that the rapid evaluation of the to-be-detected substance on the receptor activation effect is realized. According to the method, three core processes of background signal determination, to-be-detected substance signal detection and statistical analysis are completed on the molecular level by virtue of a conventional multifunctional microplate reader, so that the dependence on high-cost equipment or a complex cell model in the prior art is effectively avoided, and high efficiency, low cost and high flux of RXR alpha activator screening are realized. The method is suitable for early warning of toxicity of environmental compounds and efficient screening of RXRalpha targeted drugs, and a practical tool is provided for receptor function research and drug development.

The invention discloses a cancerous cell identification method in a TCT detection mode. The cancerous cell identification method comprises the following steps: step 1, establishing a data set and finishing arrangement; step 2, constructing a detection model; step 3, using CSPDarknet53 in the YOLO to replace a feature extraction trunk in the Faster R-CNN detection network, and optimizing the performance; and step 4, training and deploying the detection model, the stage is divided into two processes of detection model training and detection model deploying, after preliminary verification, large-scale training is performed on the detection model to obtain parameters of the final detection model, and the trained detection model is put into practical application to realize cell canceration detection. The invention belongs to the technical field of medical image analysis and artificial deep learning, and solves the problems of low cancer cell recognition efficiency and insufficient precision caused by deep feature loss and data imbalance due to complex cell boundaries in cancer cell recognition in the prior art.

The application discloses a kind of bone marrow cell identification systems based on multi-modal enhancement, comprising: cell image segmentation module, for the improved SAM model for the segmentation of bone marrow cell microscope image data;The module combines SAM model and Adapter block;Label text modification module is used to convert traditional label text into coarse and fine-grained text feature representation;Multi-modal alignment module uses an improved PMC-CLIP model to align the coarse and fine-grained text features output by the label text modification module to the image-text.The coarse-grained + fine-grained text information prompt of the present application can effectively improve the recognition accuracy of species with few cell numbers and complex cell images, solve the problem of unbalanced cell species and difficult-to-distinguish complex images, and improve the recognition accuracy of the model.

A classifier engine provides cell morphology identification and cell classification in computer-automated systems, methods and diagnostic tools. The classifier engine performs multispectral segmentation of thousands of cellular images acquired by a multispectral imaging flow cytometer. As a function of imaging mode, different ones of the images provide different segmentation masks for cells and subcellular parts. Using the segmentation masks, the classifier engine iteratively optimizes model fitting of different cellular parts. The resulting improved image data has increased accuracy of location of cell parts in an image and enables detection of complex cell morphologies in the image. The classifier engine provides automated ranking and selection of most discriminative shape based features for classifying cell types.

The application provides a cerebellar Purkinje neuron rapid identification system and method based on multi-modal deep learning, relates to the cross technical field of biomedical engineering and computer vision, and fuses specific fluorescence features and multi-dimensional morphological features, constructs a special multi-modal deep learning model, solves the interference problem of other neurons in a mixed culture system, and greatly reduces the false positive rate; a small sample learning architecture solves the industry pain point of a small amount of biological sample labeled data, improves the model generalization capability, and adapts to multi-scene sample identification. The identification system fuses Purkinje neuron specific fluorescence labeling features and cell morphological features, constructs a multi-modal deep learning recognition model based on small sample learning, is matched with a full-automatic microscopic imaging and analysis system, realizes rapid and high-accuracy identification of Purkinje neurons under a mixed culture system, does not need a complex cell purification step, greatly shortens the experimental period, and reduces the technical threshold.

This invention discloses a method for generating high-resolution microscopic cell images based on an improved HAT model. The method includes: preprocessing cell slice images captured under a microscope to construct a single-cell microscopic image dataset for training; feeding the single-cell microscopic image dataset into the improved HAT model for training; iterating the improved HAT model multiple times until the classification-perception loss function is minimized, thus obtaining the optimal-performing model; and inputting the low-resolution cell image to be tested into the optimal-performing model to obtain a high-resolution cell image. This invention can effectively recover the complex cell texture information in microscopic cell images, generating high-quality, high-resolution microscopic cell images, thereby improving the efficiency and accuracy of subsequent medical diagnosis.

The application relates to the technical field of optical engineering design, in particular to a design method of a super-structured grating, the super-structured grating comprising a grating layer, the grating layer comprising a periodic cell, the design method comprising the following steps: constructing a neural network of deep reinforcement learning, taking the current state of the cell unit as the input of the input layer of the neural network, and taking the output of the output layer of the neural network as the action of filling the cell unit; obtaining a new state of the cell unit after the action is performed; calculating the diffraction efficiency of each diffraction order of the super-structured grating in the new state; obtaining the reward return of the action according to the diffraction efficiency; updating the input of the neural network based on the reward return and propagating reversely until the terminal state of the current deep reinforcement learning is reached; and repeatedly performing the above deep reinforcement learning steps until the requirement of the optimized design is met, so that the rapid optimized design of the super-structured grating comprising a complex cell structure can be realized.

The invention relates to the technical field of image processing, and particularly discloses a cell density grouping method, device and equipment and a storage medium, and the method comprises the following steps: carrying out gradient centrifugation and micro-fluidic chip combined homogenization treatment on a cell suspension to form a single-layer or three-dimensional hydrogel embedded sample; the method comprises the following steps: based on a single-layer / three-dimensional hydrogel embedding sample, collecting two-dimensional / three-dimensional dynamic image data of cells according to a time sequence mode by applying a high-resolution optical microscope and combining a fluorescence labeling technology; through combined homogenization treatment of gradient centrifugation and a micro-fluidic chip, and in combination with a high-resolution optical microscope and a fluorescence labeling technology, a cell dynamic image in a complex cell sample is efficiently and accurately captured, and a high-quality data basis is provided for subsequent analysis; by means of self-adaptive noise reduction processing and multi-scale morphological opening and closing operation, contour parameters, texture features and spatial topological relations of cells are accurately extracted, and the feature information lays a solid foundation for accurate distinguishing of cell subgroups.

The present invention aims to provide a learning-based edge detection method that mimics the parallel and hierarchical mechanisms of biological vision, comprising the following steps: A. constructing an encoding network and a decoding network; wherein the encoding network includes a parallel processing network and a hierarchical processing network; B. inputting the original image into the parallel processing network, where it is processed by the X-cell sub-network and the Y-cell sub-network, respectively. The processing results are added and fused, and the resulting fused results are respectively input into the hierarchical processing network and the decoding network; C. The fused results are processed by the simple cell sub-network in the hierarchical processing network, resulting in simple cell processing results, which are respectively input into the complex cell sub-network and the decoding network; the complex cell sub-network processes the complex cell processing results, which are then input into the decoding network; and D. decoding by the decoding network to obtain the final detection result. This invention can achieve competitive performance while using very few parameters.

The application provides a cancer cell nucleus segmentation method based on a two-stage codec segmentation network, introduces image standardization, random cutting and splicing and affine transformation, eliminates the difference between data, and enhances the complexity of training samples; a feature extraction algorithm, a deep joint structure and a feature selection module are proposed, the feature extraction algorithm is used for extracting low-dimensional feature information, the deep joint structure is used for extracting high-dimensional feature information, and the feature selection module is used for enriching the expression ability of a feature map, finally, the inner layer decoding encoder network is used for carrying out second times of down-sampling on the feature information extracted by the outer layer encoder and feature fusion, a multi-stage skip path is introduced, different scale feature information is forwarded to the outer layer decoder, the outer layer decoder aggregates various scale feature information, fully utilizes all feature information, and can accurately segment the cell nucleus in a complex cell environment, thereby providing accurate segmentation results for subsequent quantitative analysis of the cell nucleus morphology.