Abstract: An apparatus for treating an abnormality includes a processor and a non-transitory computer readable medium that includes a first convolutional neural network (CNN) having weights and a second CNN in parallel with the first CNN and sharing the weights, the second CNN being joined to the first neural network by a distance function. The medium includes instructions that when executed by the processor implements a method. The method includes receiving a first image dataset of an area of interest and processing the first image dataset using the first CNN and receiving a second image dataset of the area of interest obtained prior to the first image dataset and processing the second image dataset using the second CNN. The method also includes identifying the abnormality using an output of the distance function wherein the identifying influences treatment of the abnormality.

Abstract: A passage timing calculation device includes a processor and a memory encoded with instructions executed by the processor, wherein the instructions causing the processor to perform operations comprising calculating a time change in an area occupied by an extraction target region that is a region in which a striated pattern appears from a plurality of images of pluripotent stem cells captured at different times, detecting a change point of the time change in an area occupied by the extraction target region, and calculating a passage timing of the pluripotent stem cells on the basis of the change point.

Abstract: Methods and systems for managing storage of data are disclosed. To manage storage of data, images may be stored across a number of storages that provide varying levels of storage performance and have correspondingly varying costs for storing data. To store the images across the storages, the images may be segmented into image segments and a likelihood of each of the image segments being used in the future may be identified. The image segments that are more likely to be used in the future may be stored in higher performance storages while the image segments that are less likely to be used in the future may be stored in lower performance storages. To identify the likelihood of each of the image segments being used in the future, the image segments may be classified based on their membership in one or more areas of interest within the images.

Abstract: Various embodiments of the present disclosure disclose methods and systems for actively monitoring an opto-fluidic instrument for vibrational disturbances and correcting images obtained during the detected disturbances. In various embodiments, an optical imaging system may acquire Z-stack images of samples supported by an XY-stage. Vibrations can cause individual stacks to be sheared, i.e., to not be co-located with respect to neighboring Z-stacks. In various embodiments, an offset between the measured positions and the expected positions of the sheared stacks may be computed, and a determination as to whether to correct or reacquire the Z-stack images may be made based at least in part on the computed offset.

Abstract: A machine learning predictor model is trained to generate a prediction of the appearance of a tissue sample stained with a special stain such as an IHC stain from an input image that is either unstained or stained with H&E. Training data takes the form of thousands of pairs of precisely aligned images, one of which is an image of a tissue specimen stained with H&E or unstained, and the other of which is an image of the tissue specimen stained with the special stain. The model can be trained to predict special stain images for a multitude of different tissue types and special stain types, in use, an input image, e.g., an H&E image of a given tissue specimen at a particular magnification level is provided to the model and the model generates a prediction of the appearance of the tissue specimen as if it were stained with the special stain. The predicted image is provided to a user and displayed, e.g., on a pathology workstation.

Abstract: The present application discloses a method for detecting image by using semantic segmentation. To input an image with data augmentation, and then encode and decode using a neural network. At least one semantically divided, and finally the at least one semantically divided is compared with the sample to classify as a target or a non-target. In this way, the CNN is used to detect whether the image is the SCC image or not, and locate the section, thereby assisting the doctor in interpreting the esophagus image.

Abstract: One or more methods of predicting expression levels. At least one of the methods includes preprocessing image data representing at least one biological image of a patient to generate preprocessed image data representing at least one preprocessed biological image of the patient; and applying a trained machine learning model to the preprocessed image data to predict, based at least partially on the at least one preprocessed biological image, an expression level of a biological indicator.

Abstract: The present disclosure relates to techniques for transforming digital pathology images obtained by different slide scanners into a common format for image analysis. Particularly, aspects of the present disclosure are directed to obtaining a source image of a biological specimen, the source image is generated from a first type of scanner, inputting into a generator model a randomly generated noise vector and a latent feature vector from the source image as input data, generating, by the generator model, a new image based on the input data, inputting into a discriminator model the new image, generating, by the discriminator model, a probability for the new image being authentic or fake, determining whether the new image is authentic or fake based on the generated probability, and outputting the new image when the image is authentic.

Abstract: A data processing system includes a cell image processing device including an image analysis unit that analyzes the acquired cell image, a storage unit that stores relative data in which the cell image, an analysis result of the cell image, and at least one or more pieces of group division information used to perform group division on the cell image are associated with each other, and a data tree creating unit that creates a virtual data tree including result information based on the analysis result to be displayed in any hierarchy of the data tree on which group division is performed so that a plurality of the relative data belong to the same group, and an information display device including a display unit configured to display the data tree.

Abstract: A method of analyzing a product includes performing an anomaly detection on a received image using an autoencoder, wherein the autoencoder includes at least one first neural network trained based on a first set of training images, and the first set of training images includes a plurality of training images each showing a corresponding defect-free product; determining, using a binary classifier, whether or not a defect is present based on a result of the anomaly detection; performing defect detection on the received image using a defect detector, wherein the defect detector includes a third neural network trained based on a one third set of training images, and the third set of training images includes a plurality of training images each showing a corresponding defective product; and evaluating a result based on a weighting of the results of the anomaly detection, the defect detection, and the binary classifier.

Abstract: An image processing using a plurality of specimen images obtained by successively applying a plurality of types of staining to a specimen to be evaluated and imaging the specimen after staining for at least two types of staining is performed. The image processing comprises: extracting an inner region corresponding to inward of a cell membrane of a single cell in the specimen based on at least one of the specimen images; specifying a cell region corresponding to an individual cell included in the specimen by expanding the inner region outwardly; and performing image cytometry for the cell region based on the specimen images. In analyzing a pathological specimen on a cell-by-cell basis, it is possible to deal with multiple immunostaining and specify the positions of individual cells and evaluate each cell separately even when a cell density in the specimen is high.

Abstract: The method for processing experimental data can include: determining experimental data (e.g., mass spectrometry spectra) and processing the experimental data. In variants, processing the experimental data can include: identifying one or more molecules, comparing experimental samples, determining a quantification, evaluating a quality of the experimental data, and/or otherwise processing the experimental data. The method can optionally include determining supplemental information, determining a set of candidate molecules, training a model, and/any other suitable steps.

Abstract: An image analyzer including: an area setting unit configured to extract a scratch area that is an area having no cells from a reference image selected from a plurality of images acquired by imaging cells in a time series and set a reference region corresponding to the scratch area in the plurality of images; a calculation unit configured to calculate an area of a cell region within the reference region and/or the ratio of an area of the cell region to the reference region from the plurality of images; and a control unit configured to cause a display device to display a change in a time series of the calculated area of the cell region and/or the ratio of the area of the cell region to the reference region.

Abstract: A method for detecting defects in appearance of a product from images thereof, applied in an electronic device, obtains positive sample images, negative sample images, and product sample images, divides the product sample images into input image blocks, and inputs the input image blocks into a pre-trained autoencoder to obtain reconstructed image blocks. The electronic device determines corresponding pixel points in the input image blocks, and corresponding pixel difference values, and generates feature connection regions of each input image block according to the positive sample images and the pixel difference values. The electronic device generates a first threshold, selects target regions from the feature connection regions and the first threshold, and generates a second threshold. The electronic device further determines a detection result of a product sample in the product sample image according to an area of the target area and the second threshold.

Abstract: The apparatus includes a processor that selects parameter-setting candidate information by referring to a database about a parameter setting history of image analysis that analyzes a cell image, and an output unit that outputs the selected parameter-setting candidate information. The database includes setting history information that is a collection of pieces of combination information indicating combinations of parameters having been set in previously-performed image analysis, and is a collection of pieces of combination information including a recognition parameter that specifies an object of image recognition and an analysis parameter that specifies what feature of the object of image recognition is focused on in performing image analysis. The processor, in response to selection of a first parameter as a recognition parameter, selects the parameter-setting candidate information based on combination information including the first parameter in the setting history information.

Abstract: A system for blob detection using deep learning is disclosed. The system may include a non-transitory computer-readable storage medium configured to store a plurality of instructions thereon which, when executed by a processor, cause the system to train a U-Net and generate a probability map including a plurality of centroids of a plurality of corresponding blobs, derive two distance maps with bounded probabilities, apply Difference of Gaussian (DoG) with an adaptive scale constrained by the two distance maps with the bounded probabilities, and apply Hessian analysis and perform a blob segmentation.

Abstract: A method (400) and a system (200) for generating a chromatically modified image of one or more components on a microscopic slide (303) is disclosed. In one aspect of the invention, the method includes obtaining the image of the one or more components on the microscopic slide (303). Additionally, the method (400) includes processing the image to identify the one or more components. The method (400) further includes segmenting at least one part of the one or more components identified from the image. Furthermore, the method (400) includes chromatically modifying the at least one part of the one or more components and generating a chromatically modified image of the one or more components.

Abstract: A method, a mobile device and a kit for performing an analytical measurement are disclosed, wherein outliers are eliminated. In the inventive method, a mobile device having a camera and a test strip for performing a color-change detection reaction are provided. A sample is applied to a test field of the test strip and an image of at least part of the test strip is captured. A region of interest in the image is determined and associated with a first sub-set of pixels. A color distribution is evaluated and outliers are eliminated in the first sub-set of pixels. A sub-region of interest is determined within the region of interest and is associated with a second sub-set of pixels. Mean values of the color distributions of the first sub-set of pixels and the second sub-set of pixels are compared to thereby determine homogeneity information of the image.

Abstract: Provided is a method for analysing a pathology image, which is performed by at least one processor and includes acquiring a pathology image, inputting the acquired pathology image into a machine learning model and acquiring an analysis result for the pathology image from the machine learning model, and outputting the acquired analysis result, in which the machine learning model is a model trained by using a training data set generated based on a first pathology data set associated with a first domain and a second pathology data set associated with a second domain different from the first domain.

Abstract: A method of characterizing cellular phenotypes includes receiving multi-parameter cellular and sub-cellular imaging data for a number of tissue samples from a number of patients or a number of multicellular in vitro models, performing cellular segmentation on the multi-parameter cellular and sub-cellular imaging data to create segmented multi-parameter cellular and sub-cellular imaging data, and performing recursive decomposition on the segmented multi-parameter cellular and subcellular imaging data to identify a plurality of computational phenotypes. The recursive decomposition includes a plurality of levels of decomposition with each level of decomposition including soft/probabilistic clustering and spatial regularization, and each cell in the segmented multi-parameter cellular and subcellular imaging data is probabilistically assigned to one or more of the plurality of computational phenotypes.

Abstract: A method for training a three-dimensional face reconstruction model includes inputting an acquired sample face image into a three-dimensional face reconstruction model to obtain a coordinate transformation parameter and a face parameter of the sample face image; determining the three-dimensional stylized face image of the sample face image according to the face parameter of the sample face image and the acquired stylized face map of the sample face image; transforming the three-dimensional stylized face image of the sample face image into a camera coordinate system based on the coordinate transformation parameter, and rendering the transformed three-dimensional stylized face image to obtain a rendered map; and training the three-dimensional face reconstruction model according to the rendered map and the stylized face map of the sample face image.

Abstract: One disclosed example method for simulated medical images using GANs includes receiving, by a generative adversarial network (“GAN”), a plurality of training images, the training images associated with an affliction and depicting different stages of progression for the affliction; generating, using the GAN, a latent space based on the training images, the latent space comprising a first set of data points indicating parameters associated with the training images; generating, using the GAN, a second set of data points in the latent space based on simulated images generated from the latent space, the simulated images based at least in part on the first set of data points; after generating the second set of data points: receiving a request for a first simulated image associated with the affliction; and generating and outputting, by the GAN, the first simulated image based on the latent space.

Abstract: The invention is to provide a microstructural image analysis device and a microstructural image analysis method capable of quantifying the relations in a plurality of regions included in a microstructural image. There is provided a microstructural image analysis device for analyzing a microstructural image. The microstructural image analysis device includes a region processing unit that extracts a first region and a second region from the microstructural image and expands the first region and the second region, an overlapping region extraction unit that extracts an overlapping region of both the first region and the second region each time the first region and the second region are expanded, and a persistence diagram generation unit that generates a persistence diagram based on a hole region generated and eliminated due to the overlapping region.

Abstract: A computer-implemented method, including the steps of: receiving video data of a human embryo, the video data representing a sequence of images of the human embryo in chronological order; applying at least one three-dimensional (3D) artificial neural network (ANN) to the video data to determine a viability score for the human embryo, wherein the viability score represents a likelihood that the human embryo will result in a viable embryo or a viable fetus; and outputting the viability score.

Abstract: Methods include applying a first stain composition comprising a fluorescent counterstain to a biological sample, measuring information corresponding to one or more stains of the first stain composition, removing the fluorescent counterstain from the biological sample, applying a second stain composition to the biological sample, measuring information corresponding to one or more stains of the second stain composition in the biological sample, where the one or more stains include a fluorescent label, and generating a first image of the biological sample, where the first image corresponds to a pattern of simulated hematoxylin staining in the biological sample.

Abstract: A method is useful for scanning partial regions of a sample by a scanning microscope, such as a laser scanning microscope or a scanning electron microscope, and for reconstructing an overall image of the sample from data of the scanned partial regions of the sample. The method includes: 1) determining partial regions of the sample, which are scanned by the scanning microscope, by a machine learning system which is trained by supervised learning, unsupervised learning, and/or reinforcement learning for improved determination of the partial regions of the sample which are scanned by the scanning microscope; 2) scanning the determined partial regions of the sample by the scanning microscope; and 3) reconstructing the overall image of the sample from the data of the scanned partial regions of the sample, wherein non-scanned partial regions of the sample are estimated by the data of the scanned partial regions of the sample.

Abstract: Systems and methods are provided for determining if a subject has a biological condition from a dried fluid sample. A fluid sample from a subject is dried in a microfluidic device to provide a dried fluid sample. The dried fluid sample is imaged at a camera to provide a sample image, and the sample image is provided to a computer vision mode. At the computer vision model, it is determined if the sample image contains a ferning pattern indicative of a biological condition of the subject.

Abstract: A method of using machine learning to output task-specific predictions may include receiving a digitized cytology image of a cytology sample and applying a machine learning model to isolate cells of the digitized cytology image. The machine learning model may include identifying a plurality of sub-portions of the digitized cytology image, identifying, for each sub-portion of the plurality of sub-portions, either background or cell, and determining cell sub-images of the digitized cytology image. Each cell sub-image may comprise a cell of the digitized cytology image, based on the identifying either background or cell. The method may further comprise determining a plurality of features based on the cell sub-images, each of the cell sub-images being associated with at least one of the plurality of features, determining an aggregated feature based on the plurality of features, and training a machine learning model to predict a target task based on the aggregated feature.

Abstract: There is provided a cell analysis apparatus that comprises image capture circuitry for capturing a brightfield image of a cell using brightfield imaging. The cell has been dyed by a functional dye that indicates, during fluorescence imaging and during brightfield imaging, whether the cell has a given characteristic. A model derived by machine learning is stored and used in combination with the brightfield image to determine whether the cell has the given characteristic. There is also provided a method for creating a cell categorisation model, comprising applying a functional dye to one or more samples comprising a plurality of cells. The functional dye indicates during fluorescence imaging and during brightfield imaging whether each of the cells has a given characteristic.

Abstract: An image display method according to this invention includes obtaining an image set including a plurality of stained images, the plurality of stained images being obtained by imaging a multiple immunostained tissue specimen, a registration processing being performed for mutual registration for the plurality of stained images, and switching and displaying the stained images included in the image set on a screen in accordance with a predetermined switch rule with a result of the registration processing reflected. An image includes at least one of the stained images and a graphical user interface for receiving an operation input from a user for editing the switch rule being displayed on the screen. The switch rule is changed and set according to the operation input. The image is displayed on the screen in accordance with the changed and set switch rule.

Abstract: An apparatus and method for detecting content of interest on a slide using machine learning. The apparatus includes at least a processor and a memory communicatively connected to the at least a processor. The memory instructs the processor to receive a first image, comprising a macro image, identify areas of interest associated with the grids of the first image, receive a second image comprising a high magnification image associated with the areas of interest of the first image, classify, using at least a probed point, the grids of the first image, wherein classifying the grids of the first image includes classifying the grids into accepted grids of the grids and rejected grids of the grids, scan, using the image capturing device, the accepted grids to generate an output image, and display, using a display device, the output image.

Abstract: Disclosed are apparatuses, systems, and techniques to render images depicting light interacting with media that have volume attenuation, using optimized spectral rendering that emulates rendering of the media in tristimulus color rendering schemes.

Abstract: A method comprising receiving images depicting stained target tissue, segmenting the images into cell type and region type segmentations, extracting cell phenotype features from an analysis of the stains for cell type segmentations, clustering the cell type segmentations, computing feature vectors each including the respective cell phenotype features, and an indication of a location of the cell type segmentation relative to region type segmentation(s), creating a cell-graph based on the feature vectors of cell type segmentations and/or clusters, wherein each node denotes respective cell type segmentation and/or respective cluster and includes the feature vector, and edges represent a physical distance between cell type segmentations and/or clusters corresponding to the respective nodes, inputting the cell-graph into a graph neural network, and obtaining an indication of a target therapy likely to be effective for treatment of medical condition in the subject as an outcome of the graph neural network.

Abstract: Provided are a sample image analyzer and a corresponding method. The sample image analyzer includes: an object stage for supporting a sample carrier; an imaging device for capturing an image of an object in a sample on the sample carrier; a driving device for driving the object stage and the imaging device to move relative to each other; and a control device configured to control the driving device to deliver the sample carrier to a position below the imaging device, control the driving device to drive the object stage and the imaging device to move horizontally relative to each other, and to move vertically relative to each other, control the imaging device to capture, at least during the relative vertical movement, images of the object at different horizontal positions and at different vertical positions, and fuse the images of the object to obtain a target image of the object.

Abstract: One aspect provided herein is an analyte processing device, comprising one or more flow channels, wherein at least one flow channel of the one or more flow channels comprise an analyte processing area; one or more excitation sources in optical communication with the analyte processing area and comprising an optical path from the one or more excitation sources to the analyte processing area; and one or more photodetectors in optical communication with the analyte processing area, wherein the optical path comprises a light scattering control system.

Abstract: A microfabricated device defining a high density array of microwells is described for cultivating cells from a sample. The device may be incubated to grow a plurality of cells, which may be split into an analysis portion and a reserve portion. Methods are provided for screening a biological entity of interest using the microfabricated device, for example, for screening phosphate solubilizing bacteria or other bacteria producing acids.

Abstract: A diagnosis support program causes a computer to execute a derivation procedure of deriving, on the basis of a first pathological image corresponding to a first affected tissue, history information regarding a history of viewing the first pathological image, and diagnostic information for the first affected tissue corresponding to the first pathological image, diagnosis support information for supporting diagnosis of a second pathological image corresponding to a second affected tissue to be diagnosed.

Abstract: Techniques for classifying biomedical image data using a graph neural network are disclosed. In one particular embodiment, the techniques may be realized as a method for classifying biomedical image data comprising generating an annotated representation of biomedical image data; identifying a plurality of pixel clusters based on the biomedical image data; constructing a graph based on the plurality of pixel clusters; determining at least one biomedical feature for at least one node of the graph based on the annotated representation of the biomedical image data; and processing a graph neural network to classify the biomedical image data based on the at least one biomedical feature.

Abstract: Methods and systems for evaluating a query perturbation, in a cell based assay representing a test state, are provided. Control data points having dimensions representing measurements of different features across control cell aliquots are obtained. Test data points having dimensions representing measurements of different features across test cell aliquots are obtained. A composite test vector is computed between measures of central tendency across the control data points and measures of central tendency across the test data points. Query perturbation data points having dimensions representing measurements of different features across perturbation cell aliquots are obtained. A composite query perturbation vector is computed between measures of central tendency across the control data points and measures of central tendency across the plurality of query perturbation data points.

Abstract: A biological fluid filtration system for scanning a biological fluid so as to filter potentially undesirable constituents from the biological fluid for therapeutic or diagnostic purposes. The biological fluid filtration system generally includes a fluid receiving device adapted to receive a biological fluid. A valve including an inlet, a first outlet, and a second outlet is fluidly connected to the fluid receiving device. The biological fluid within the fluid receiving device is scanned by a scanner to produce scanned data relating to the biological fluid. A control unit in communication with the scanner and the valve receives the scanned data and controls the valve based on the scanned data. The valve is controlled to direct the biological fluid through either the first or second outlet of the valve depending upon the constituents of the biological fluid identified by the control unit.

Abstract: A system for dissociating cells from a cell culture vessel. The system comprises an imaging system configured to image a plurality of cells in a cell culture vessel being dissociated from at least one surface of the cell culture vessel by at least one cell dissociation agent; and at least one controller coupled to the imaging system and configured to: control the imaging system to capture a sequence of images of at least some cells in the plurality of cells during dissociation; and identify when to neutralize the at least one cell dissociation agent using the sequence of images.

Abstract: An operational unit for locating and neutralizing pathogen cells in blood includes a cassette which has a plurality of thin holding chambers that are filled with blood drawn from a patient. A light source illuminates the holding chambers and passes light to an underlying sensor array such that the cells in the blood selectively block the light to produce shadow images of the cells. A processor performs pattern recognition to locate the pathogen cells by use of an image library. After the pathogen cells are located, a source of ultraviolet light is activated and UV light is passed through selectively controlled shutters to illuminate only the limited areas that have the identified pathogen cells. Sufficient ultraviolet light energy is applied to destroy the identified cells. A pump refills the cassette holding chambers, returns the neutralized-pathogen blood to the patient, and the process is repeated.

Abstract: A microfluidic-device observation apparatus 1 for observing a specimen present in a plurality of flow paths 103a to 103e arranged in a microfluidic device 100 is provided with: an imaging unit 4 configured to acquire an image of the microfluidic device 100; an extraction pixel selection unit 21 configured to select extraction pixels from a plurality of pixels by a certain criterion based on luminance values of the plurality of pixels constituting the acquired image; a flow path identification unit 22 configured to locate the plurality of flow paths 103a to 103e included in the image; a specimen-featured-pixels detection unit 24 configured to detect a certain number or more of extraction pixels consecutively present inside of the identified plurality of flow paths 103a to 103e as a specimen-featured-pixels group; and a statistical feature value calculation unit 26 configured to calculate a statistical feature value of the specimen based on the number of specimen-featured-pixels group and/or the number of the e

Abstract: In accordance with some embodiments of the disclosed subject matter, systems, methods, and media for automatically transforming a digital image into a simulated pathology image are provided. In some embodiments, the method comprises: receiving a content image from an endomicroscopy device; receiving, from a hidden layer of a convolutional neural network (CNN) trained to recognize a multitude of classes of common objects, features indicative of content of the content image; receiving, providing a style reference image to the CNN; receiving, from another hidden layer of the CNN, features indicative of a style of the style reference image; receiving, from the hidden layers of the CNN, features indicative of content and style of a target image; generating a loss value based on the features of the content image, the style reference image, and the target image; minimizing the loss value; and displaying the target image with the minimized loss.

Abstract: A biological fluid filtration system for scanning a biological fluid so as to filter potentially undesirable constituents from the biological fluid for therapeutic or diagnostic purposes. The biological fluid filtration system generally includes a fluid receiving device adapted to receive a biological fluid. A valve including an inlet, a first outlet, and a second outlet is fluidly connected to the fluid receiving device. The biological fluid within the fluid receiving device is scanned by a scanner to produce scanned data relating to the biological fluid. A control unit in communication with the scanner and the valve receives the scanned data and controls the valve based on the scanned data. The valve is controlled to direct the biological fluid through either the first or second outlet of the valve depending upon the constituents of the biological fluid identified by the control unit.

Abstract: An image acquisition and analysis system are disclosed. The system enables high throughput, objective analysis of microbial samples over days or weeks. The system may accommodate upwards of twelve 96- or 384-well plates simultaneously (liquid or solid media). The system may acquire and analyze a large number of samples in a short period of time. For example, over 384 samples per minute or 18,432 samples per hour. The system hardware may include a multi-spectral imager (fluorescence and bright field detection), electro-mechanical assemblies, and an optional high-resolution stage. The system may automate image acquisition, image data processing, simplify data storage, and enable automated analysis tools to significantly reduce the manual labor and time associated with such tasks. The system may allow for quick processing and analysis of data into clear phenotypic classes.

Abstract: Methods and systems for determining interaction between cells are described wherein the method includes determining or receiving a sequence of images representing manipulating first cells, in a holding space, the holding space including a functionalized wall comprising second cells, the manipulating including settling of the first cells onto the functionalized wall and applying a force on the settled first cells; detecting groups of pixels representing first cells in first images representing the settling of the first cells onto the functionalized wall; tracking locations of detected first cells in the first images; and, determining settling events, a settling event being determined if a cell in a first image is not distinguishable from background of the first image, the location in the image at which a cell settling event is detected defining a cell settling location; detecting groups of pixels representing cells in second images captured during the application of the force and tracking locations of detected

Abstract: Disclosed in one aspect is a method for performing a complete blood count (CBC) on a sample of whole blood by metering a predetermined amount of the whole blood and mixing it with a predetermined amount of diluent and stain and transferring a portion thereof to an imaging chamber of fixed dimensions and utilizing an automated microscope with digital camera and cell counting and recognition software to count every white blood cell and red blood corpuscle and platelet in the sample diluent/stain mixture to determine the number of red cells, white cells, and platelets per unit volume, and analyzing the white cells with cell recognition software to classify them.

Abstract: Provided is a method and system for predicting tumor mutation burden (TMB) in triple negative breast cancer (TNBC) based on nuclear scores and histopathological whole slide images (WSIs). The method includes the following steps: first, screening the histopathological WSIs of TNBC; calculating a TMB value of each patient according to gene mutation of each patient with TNBC, and dividing the TMB values into two groups with high and low TMB according to a set threshold; dividing the histopathological WSIs of TNBC into patches of a set size; screening a certain number of patches with high nuclear scores according to a nuclear score function; then building a convolutional neural network (CNN) classification model, and stochastically initializing parameters in the CNN classification model; and finally, putting the screened patches into the built CNN classification model for training, so as to automatically predict high or low TMB with the histopathological WSIs of TNBC.

Abstract: A deep learning-based digital staining method and system are disclosed that provides a label-free approach to create a virtually-stained microscopic images from quantitative phase images (QPI) of label-free samples. The methods bypass the standard histochemical staining process, saving time and cost. This method is based on deep learning, and uses a convolutional neural network trained using a generative adversarial network model to transform QPI images of an unlabeled sample into an image that is equivalent to the brightfield image of the chemically stained-version of the same sample. This label-free digital staining method eliminates cumbersome and costly histochemical staining procedures, and would significantly simplify tissue preparation in pathology and histology fields.