39results about "Microscopic object acquisition" patented technology

The application discloses a kind of activated sludge state evaluation method, equipment and medium based on microscopic video, the application relates to sewage treatment intelligent detection technical field, activated sludge state evaluation method based on microscopic video includes: control sludge sample moves according to preset mode, and obtains microscopic video stream for sludge sample;Based on preset frame extraction mode, obtain the multiple frames of microscopic video images corresponding to the microscopic video stream;According to the feature vector of each frame of microscopic video image, based on graph learning obtains the sample comprehensive characteristics corresponding to sludge sample;Sample comprehensive characteristics are input into pre-trained evaluation model, and the state parameter of sludge sample is determined according to the model output of evaluation model.The application can realize the quantitative evaluation of the overall state of activated sludge, avoid the limitation of single frame image representation.

The present application relates to a cell sorting method and a cell display method. The cell sorting method includes: acquiring cell image data sent from a cell sorting device (202); locating cells to be sorted in the cell image data through a deep learning model (204); evaluating fluorescence signal intensities of the cells to be sorted based on the cell image data (206); and aspirating a cell meeting a preset sorting condition from the cells to be sorted according to the fluorescence signal intensities of the cells to be sorted (208).

An apparatus and method for inline scanned image enrichment is provided. The apparatus includes a computing device configured to receive a plurality of subject data, generate a candidate set to model the scan focal points from, digitally capture the slide using the identified focal points through machine-learning processes, processing the captured image to optimize its viewability, and storing the captured image in an accessible repository.

The present embodiments relate to cell confluency estimation and manufacturing. Subject matter of the present embodiments provides computer-implemented methods, computer systems and computer-readable storage media for predicting the results of image-based cell confluency estimation and manufacturing methods.

Automated systems and methods for evaluating specimens affixed to substrates, such as slides, an exemplary system including a slide imager configured for acquiring a plurality of micro images of a specimen affixed to an substrate, the specimen including a plurality of objects distributed within a three-dimensional volume, and for generating a whole specimen image of the specimen using the micro images, wherein objects contained in the specimen are depicted substantially in focus in the whole specimen image regardless of a z-depth of the respective objects within the specimen. The whole specimen image is stored on a storage medium for subsequent review by a cytotechnologist using a computer-controlled review station including a display and a user interface, wherein the review station user interface is configured such that the cytotechnologist can review and classify the stored whole specimen images.

Techniques for measuring single synaptic signals under varying experimental conditions include controlling a video recording microscope to capture, at multiple different times, a first imaged area in a sample holder as a video frame when the sample holder is disposed on a stage and holds a sample of neuronal tissue combined with at least one fluorophore that emits a corresponding electromagnetic wavelength in a synapse during synaptic activity. At least one synaptic region of interest is determined based on a group of pixels in the first imaged area that record electromagnetic emissions from the fluorophore at the different times. An ordered time series of emission intensity is recorded in each of the synaptic region of interest. Peak emission intensity values in the time series are corrected for transmitter label transients. The ordered time series with corrected peak emission intensity values are stored in a data structure with a standard format.

A detection method includes: preparing sample image data of a sample in which a target substance is labeled with a labeling substance; acquiring first background image data in which an image feature amount of a single bright spot in the sample image data is reduced by a first filter; acquiring second background image data in which an image feature amount of a dense bright spot in the sample image data is reduced by a second filter; synthesizing the first background image data and the second background image data on a basis of brightness information of the sample image data and acquiring synthesized background image data; and obtaining difference image data that is a difference between the sample image data and the synthesized background image data.

The present application provides an apparatus, a system, a method and a computer program product for extracting images of microorganisms, the apparatus comprising: an acquisition unit configured to accept a plurality of captured images of a flow path in which microorganisms flow; and an extraction unit configured to extract a plurality of images of the microorganisms of the same individual from the plurality of captured images. In the above apparatus, the flow path can have a vortex generator configured to generate a vortex in a capturing range of the flow path in which the plurality of captured images are captured. In any one of the above apparatuses, the acquisition unit can accept a plurality of captured images of the flow path captured at different timings.

Methods for identifying micron-scale features below a surface of a tissue include emitting from one or more emitters at the surface of the tissue electromagnetic signals capable of penetrating tissue of different densities; obtaining from a sensor positioned at the surface of the tissue electromagnetic signals reflected from or transmitted through tissues of different densities as one or more obtained images; inputting the one or more obtained images into a machine learning model, wherein the machine learning model is trained to: identify scattering of certain electromagnetic signals comprising each of the one or more obtained images; correct for the scattering to create one or more images tissues at one or more subsurface depths; and identify micron-scale features of interest within the one or more images of tissues at the one or more subsurface depths.

The present invention provides an apparatus, method, and program for extracting multiple images of the same microorganism from multiple captured images. [Solution] In the system 10, the discrimination device 60 includes an acquisition unit that receives multiple images of the flow channel 24 through which microorganisms in the flow channel device 20 flow, and an extraction unit that extracts multiple images of the same individual microorganism from the multiple images. The flow channel through which microorganisms flow may have a vortex generator that generates vortices in the imaging range 26 that captures multiple images within the flow channel. The acquisition unit receives multiple images of the flow channel through which microorganisms flow, taken at different timings. The acquisition unit also receives multiple images taken from two or more different directions.

Methods and systems for selecting cellular bodies are disclosed. The method comprises determining or receiving first and second images of first and second cellular bodies in a holding space. The first and second images are obtained with first and second imaging modalities. Each pixel in the first image may be associated with a pixel in the second image. A set of first pixels representing first cellular bodies in the first image, and groups of second pixels representing the second cellular bodies in the second image are detected. For each second cellular body, an interaction parameter is determined between the respective second cellular body and one or more of the first cellular bodies. The parameter may represent a contact surface between the respective second cellular body and the first cellular bodies. Groups of second pixels are selected for which the determined parameter is greater than or smaller than a threshold.

The present invention relates to a method of characterizing a microorganism, comprising: A. for each wavelength of a predetermined set of wavelengths comprising at least one wavelength, acquiring a holographic digital image, generating a focused image by a computer device, each pixel of the image comprising an amplitude value and a phase value, and segmenting the focused image to extract a portion corresponding to the microorganism, and B. characterizing the microorganism by a computer device according to the aggregated image portion. According to the invention, before characterization or before segmentation or before generation of aggregated images, the method comprises correcting the optical aberration of the acquisition device by means of a computer device, and characterizing the microorganism comprises applying a digital model to these parts, the amplitude value and / or phase value of each wavelength of the predetermined set of wavelengths as a descriptor.

The present inventive concept relates to a microscope system and a method for processing a plurality of digital images of a sample. The method comprises: acquiring a first input set of digital images by: illuminating, by an illumination system, the sample with a first subset of a plurality of illumination patterns, and capturing a digital image of the sample for each illumination pattern of the first subset of the plurality of illumination patterns, thereby forming the first input set of digital images; inputting the first input set of digital images into a first set of machine learning models configured to output a first inference output; acquiring a second input set of digital images by: illuminating, by the illumination system, the sample with a second subset of the plurality of illumination patterns, and capturing a digital image of the sample for each illumination pattern of the second subset of the plurality of illumination patterns, thereby forming the second input set of digital images; inputting the second input set of digital images into a second set of machine learning models configured to output a second inference output, wherein the second set of machine learning models is different from the first set of machine learning models; and inputting the first inference output and the second inference output into an image processing machine learning model being trained to process the plurality of digital images of the sample using the first inference output and the second inference output.

A method and a device are for training a machine learning model to construct a digital image depicting a focused sample. The method includes acquiring a training set of digital images of a training sample by: positioning the training sample, relative to a microscope objective, at a focus position outside a range of positions between a near limit and a far limit of a depth of field of the microscope objective; illuminating the training sample with a plurality of illumination patterns, and capturing, for each illumination pattern of the plurality of illumination patterns, a digital image of the training sample; receiving a ground truth having a digital image depicting the training sample being in focus; and training the machine learning model to construct the digital image depicting a focused sample using the training set of digital images and the ground truth.

The application discloses a kind of based on deep learning's pathological image proteomics analysis method and system, it is related to bioinformatics, the method includes: using laser microdissection and mass spectrometry constructs paired image-protein dataset;Adopt pre-training VGG16 convolutional neural network to extract image deep feature, fusion cell morphological feature constructs whole proteome regression mapping model;Through U-Net single cell recognition and iterative deconvolution algorithm output cell level protein expression matrix;Combining mixed semi-supervised learning strategy handles label scarcity problem;Based on protein expression matrix, dimension reduction clustering, spatial heterogeneity quantification (CV+SHI) and visual analysis are carried out.The application realizes the regression mapping of pathological image to whole proteome (>2800) for the first time, breaks through the flux bottleneck of traditional virtual staining, realizes true single cell resolution proteomics, and provides new means for precision medicine.

The application discloses a probe tip recognition method in a microscopic image, a probe tip recognition device in a microscopic image, an electronic device and a storage medium, and belongs to the technical field of probe positioning of a probe station. The probe tip recognition method in the microscopic image comprises the following steps: acquiring a probe gray-scale image; converting the probe gray-scale image into a tip feature binary image; screening a connected domain with an edge topography conforming to a probe tip shape from the tip feature binary image as a tip connected domain; and generating a tip coordinate based on the tip connected domain. The method can effectively filter out interference substances with similar brightness to the probe tip through edge topography screening, thereby improving the accuracy and stability of probe tip recognition.

The sample is held by a sample stage in the microscope system and milled to expose a region of interest (ROI) within the sample. The sample is milled based on the ROI location determined by sample images acquired with light beams irradiated from different axes. Sample images are acquired while the sample is held using the same sample stage for milling.

An image processing method includes acquiring an image in which a cell structure having a stained vascular network structure is imaged, applying a wavelet transform to the image such that a contour image in which contours of the vascular network structure are extracted is generated, and repeatedly excluding object pixels from object boundaries recognized in the contour image such that a skeleton image in which skeletons having a line width of a predetermined number of pixels are extracted is generated.

The present inventive concept relates to a method (30) and a device (10) for training a machine learning model to construct a digital image (602) depicting an artificially stained sample, the method (30) comprising: receiving (S300) a training set of digital images of an unstained sample, wherein the training set of digital images is acquired by illuminating the unstained sample from a plurality of directions and capturing a digital image for each of the plurality of directions; receiving (S302) a ground truth comprising a digital image of a stained sample, wherein the stained sample is formed by applying a staining agent to the unstained sample; and training (S304) the machine learning model to construct a digital image (602) depicting an artificially stained sample using the received training set of digital images of the unstained sample and the received ground truth. The present inventive concept further relates to a microscope system (20) and a method (40) for constructing a digital image (602) depicting an artificially stained sample.

Methods for identifying micron-scale features below a surface of a tissue include emitting from one or more emitters at the surface of the tissue electromagnetic signals capable of penetrating tissue of different densities; obtaining from a sensor positioned at the surface of the tissue electromagnetic signals reflected from or transmitted through tissues of different densities as one or more obtained images; inputting the one or more obtained images into a machine learning model, wherein the machine learning model is trained to: identify scattering of certain electromagnetic signals comprising each of the one or more obtained images; correct for the scattering to create one or more images tissues at one or more subsurface depths; and identify micron-scale features of interest within the one or more images of tissues at the one or more subsurface depths.

Methods of aligning specimen images of specimen sections situated on a substrate include obtaining an optical or SEM image of the substrate and locating and aligning optical or SEM images of each specimen section. The specimen sections are then imaged with an SEM to obtain preview images, and a region of interest (ROI) in at least one of the preview images is selected. The preview images are processed so that at least portions of the preview images proximate the ROI are aligned. Based on the alignment of the preview images, final SEM image of selected specimen sections are obtained so that a set of images aligned in three dimensions is available. Image alignment can use cross-correlation with a fixed or variable reference that can be updated as specimen section images are processed.

High Throughput Single Molecule Tracking (htSMT) systems and methods are described wherein the htSMT workflows are adapted to characterize both known and novel pathway contributions to interaction networks in live cells, such as protein signaling interaction networks.

A method for retrieving a target position in a microscopic sample using position retrieval information, the position retrieval information including a set of geometric descriptors describing a spatial relation between a target position identifier and a plurality of reference position identifiers corresponding to positions of a plurality of reference markers. The method includes providing a representation of the sample or a region thereof expected to comprise the target position; specifying a potential one of the reference markers associated to the target position in the representation; providing digital distance representations of the individual reference marker distances of the plurality of reference markers associated to the target position in a form of rotational traces coaxially centred around the potential one of the reference markers specified; and identifying a feature in the representation as potentially being the target position based on an evaluation of the representation and the digital distance representations.

A current observation area is determined exploratorily from among a plurality of candidate areas (300), on the basis of a plurality of observed areas (302) in a biological tissue. A plurality of reference images (208) obtained by means of low-magnification observation of the biological tissue are utilized at this time. A learning image is acquired by means of high-magnification observation of the determined current observation area. A plurality of convolution filters included in an estimator can be utilized to evaluate the plurality of candidate areas (300).

This invention provides an automatic SEM image classification method and electronic device based on an improved ConvNeXt network model. The method involves acquiring a target image using a scanning electron microscope (SEM); the target image is a microscopic electron microscope image; the target image is input into an improved ConvNeXt network model to obtain the probability of the target image belonging to each image category; the ConvNeXt network model includes a channel attention mechanism (ECA) module and a global attention mechanism (GAM) module; the image category corresponding to the highest probability is determined as the target image category. Compared to existing technologies, by introducing the channel attention module (ECA) and the global attention mechanism (GAM), the interaction information between different channels can be effectively captured during training, and the network pays more attention to important information and suppresses interference from irrelevant information during learning, thus improving the image classification ability.

The application provides an end-to-end intelligent control method and system of a scanning electron microscope, and relates to the technical fields of micro-nano control and machine vision. The application converts a starting position bounding box (starting end) and a target position bounding box (end point end) into a starting heat map and a target heat map respectively, splices a current scene image, the starting heat map and the target heat map to form a multi-channel input tensor, extracts a multi-scale spatial feature map from the multi-channel input tensor through a feature extraction network, and finally inputs the multi-scale spatial feature map into a trajectory generation network, so that multi-level visual features effective for a control task can be extracted from the fused input. The sequence model characteristics can be utilized by generating the trajectory coordinate sequence in a self-recurrent manner, so that a nano-level resolution trajectory coordinate smooth, continuous and conforming to the physical motion law can be generated.

A system and procedure are provided for collecting and analyzing airborne particles at a user's site. The system includes a blower module for mobilizing dust from surfaces, a sampling system with an integrated vacuum pump for collecting particles on a slide for microscopic examination, and a mobile microscope for analyzing the collected particles. The system also includes an artificial intelligence (AI) module for classifying and counting particle types, and an app connectivity module for wireless communication with a mobile device. The procedure involves using the powerful blower to remove dust from surfaces, collecting particles on a slide, and analyzing the collected particles using the mobile microscope and the AI ​​modules.The system enables the analysis of airborne particles and allows users to detect and monitor particle concentrations in their environment. The system is delivered in a shipping / packaging box.

The application discloses a multi-cell post-positioned carbon filter pool disinfection control method and system, the method comprising: sampling and obtaining water samples corresponding to each cell carbon filter body in the activated carbon filter pool; obtaining plankton data corresponding to the water samples; calculating the plankton accumulation according to the plankton data and the unit water collection amount, judging the evaluation level of the plankton accumulation; determining the alarm level according to the evaluation level of the plankton accumulation and feeding back the alarm information, and determining the disinfection level according to the evaluation level of the plankton accumulation and executing the disinfection operation. The application respectively samples and disinfects each cell carbon filter body of the activated carbon filter pool, compared with the existing overall disinfection, the operation is flexible, does not need to stop production completely, reduces the negative influence caused by disinfection, can accurately control the dosing amount, aeration or backwashing and the like of each sub-cell carbon filter body, reduces the use amount of the medicine, and reduces the cost.