5 results about "Cellular level" patented technology

This application provides a method, apparatus, device, and medium for detecting physiological state. The method includes: first, acquiring the potential signal and environmental parameters from the skin surface of the worker; then, processing the potential signal using a signal inversion algorithm to determine the cell ion concentration; next, extracting the characteristic frequencies of the environmental parameters if the cell ion concentration is within a preset threshold; further, calculating a dynamic equilibrium coefficient based on the cell ion concentration, potential signal, and characteristic frequencies; and finally, determining the worker's physiological state based on the dynamic equilibrium coefficient. This method enables early identification of latent fatigue at the cellular level, improving workplace safety.

This utility model relates to the field of confocal systems and electromagnetic equipment technology, and discloses a coil structure for use in a confocal system, placed on a confocal lens. The structure includes: a ring-shaped magnetic core with a placement notch; the placement notch is used to place a cell container, with the confocal lens located below the cell container; a hollow coil wound around the magnetic core; and a coolant circulation mechanism connected to the coil, which is used to introduce a cooling medium into the coil to cool the coil structure. This coil structure can be placed in the lens area to operate, avoiding excessive attenuation of the magnetic field strength. The hollow coil allows the coolant to circulate within it and carry away the heat generated by the coil, avoiding the risk of heating the lens when using the coil directly. It solves the compatibility problem between alternating magnetic fields and confocal microscopes, and provides a reliable solution for studying the effects and mechanisms of alternating magnetic fields at the cellular level.

The universal biomarker array enables diagnosis and localization of disease states earlier than now recognizable, and overall increases the accuracy of diagnosing disease states. A universal biomarker array is formed from a series of mathematical parameters calculated from digital tissue images showing tissue details at cellular levels. The universal biomarker array includes one or more novel arrays of parameters (i.e., a spatial entropy array, a bin array, and / or a quartile array) in combination with one or more arrays of prior art parameters (i.e., a pattern array, a distance array, and / or a morphological array) and / or in combination with one or more other parameters. The AI / ML system can be used to analyze universal biomarker arrays relative to database-based reference data for early diagnosis and localization of disease processes.

The invention belongs to the technical field of single cell data processing, and particularly relates to a single cell time sequence data simulation and completion method and system. The method comprises the following steps that interpolation is carried out on hidden space vector representation in a time starting point and end point single cell matrix variational auto-encoder (VAE) model, then interpolation is carried out on the two vectors in a hidden space, and a middle time point hidden space vector is generated; finally, the vectors are reduced into a gene expression matrix through a decoder, so that missing or unobserved single cell data at the middle moment in the time sequence are simulated, the single cell data in the time sequence can be simulated through the method, and therefore the continuous change of the cell state can be deduced and complemented; the method is suitable for single cell level pedigree reconstruction and trajectory analysis in dynamic biological processes such as development, aging and disease progression, and has high biological interpretation value and practical application significance.

The invention discloses a pathological image proteomics analysis method and system based on deep learning, and relates to bioinformatics, and the method comprises the steps: constructing a paired image-protein data set through laser microdissection and mass spectrometry; a pre-trained VGG16 convolutional neural network is adopted to extract image deep features, and cell morphological features are fused to construct a whole proteome regression mapping model; outputting a cellular level protein expression matrix through a U-Net single cell recognition and iterative deconvolution algorithm; processing a label scarcity problem in combination with a hybrid semi-supervised learning strategy; and carrying out dimensionality reduction clustering, spatial heterogeneity quantification (CV + SHI) and visual analysis based on the protein expression matrix. According to the method, the regression mapping from the pathological image to the whole proteome (gt; 2800) is realized for the first time, the flux bottleneck of traditional virtual staining is broken through, real single cell resolution proteomics is realized, and a new means is provided for precise medical treatment.