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: 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: 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: 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: 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: 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: 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 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: 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: 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: 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: 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: 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: 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 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: 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: 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: 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: 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: 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.

Abstract: An image processing device includes a cell analyzer that analyzes an image of cells cultured within a culture container and that acquires the number of cell divisions experienced by each cell in the image, and also includes a statistical analyzer that calculates a statistical value indicating differentiation potency of each cell in the image from the number of cell divisions acquired by the cell analyzer. The statistical analyzer creates a frequency distribution of the number of cell divisions, and the statistical value represents a bias in the frequency distribution.

Abstract: A medical image processing apparatus including an obtaining unit configured to obtain a plurality of tomographic images obtained by radially scanning measuring light on an eye to be examined, and corresponding to a plurality of locations of the eye to be examined, respectively, and an imaging parameter corresponding to each tomographic image, a modifying unit configured to modify a shape of a tomographic image corresponding to the imaging parameter by using the imaging parameter, and an aligning unit configured to align a plurality of shape-modified tomographic images with each other.

Abstract: A classification model for identifying or classifying biological structures depicted in a base image can be generated by training a label generation model and then using the label generation model to train the classification model. The label generation model can be configured to accept co-registered base and informer images, while the classification model can be configured to accept base images. The classification model can output an indication when a biological structure is identified or classified in a base image.

Abstract: Disclosed herein are a system for identifying cells on a microscopic image. According to some embodiments, the system comprises a non-transitory processor-readable medium, and a processor communicably configured to receive the microscopic image, and process the received microscopic image with a convolutional neural network (CNN) model having a modified U-Net architecture. Also disclosed herein are methods for identifying a spatial pattern of human induced pluripotent stem cells (hiPSCs) by using the present system.

Abstract: An AI-enhanced data labeling tool assists a human operator in annotating image data. The tool may use a segmentation model to identify portions to be labeled. Initially, the operator manually annotates portions and once the operator has labeled a sufficient number of portions, a classifier is trained to predict labels for other portions. The predictions generated by the classifier are presented to the operator for approval or modification. The tool may also include an active learning model that recommends portions of the image data for the operator to annotate next. The active learning model may suggest one or more batches of portions based on the extent to which, once labeled, those batches will increase the diversity of the total set of labeled portions.

Abstract: Disclosed is a method for automatic classification of pathological images based on a staining intensity matrix. This method directly extracts the staining intensity matrix irrelevant to a stain ratio, a staining platform, a scanning platform and some human factors in the pathological image as the feature information of classification, without restoring normalized stained images, while retaining all impurity-free information related to diagnosis. It avoids the phenomenon that the diagnostic effect of the existing computer-aided diagnosis method of pathological images based on the traditional color normalization method changes with the changes of the selected standard pathological sections. Moreover, it avoids the error introduced by the need to restore the stained image, and has a higher diagnostic accuracy and a more stable diagnostic effect. At the same time, the method can realize the diagnosis of pathological images in a shorter time, which is easy to realize and more practical.

Abstract: Machine learning approach can combine mass spectral imaging (MSI) techniques, one with low spatial resolution but intact molecular spectra and the other with nanometer spatial resolution but fragmented molecular signatures, to predict molecular MSI spectra with submicron spatial resolution. The machine learning approach can perform transformations on the spectral image data of the two MSI techniques to reduce dimensionality, and using a correlation technique, find relationships between the transformed spectral image data. The determined relationships can be used to generate MSI spectra of desired resolution.

Abstract: A system and method for delivering diagnostic information to a user in an automated manner. An image processing module reads magnified raw image data from whole slides containing tissue cells. A background deletion process identifies and isolates cell images. A neural network, which is trained based upon image data, classifies the cell images. The classification uses specialist criteria to categorize/segment the cell images into a plurality of discrete cell types. A display process provides the diagnostic information to the user. The neural network can be trained using a plurality of cell types each having the specialist criteria. The diagnostic information includes filtered and/or reorganized images of the tissue cells. Additionally, the user can request the diagnostic information based upon an account that provides payment according to a predetermined formula associated with at least one of a type, format, and timing of information delivered to the user.

Abstract: An image analysis method for determining the biomedical state of a tissue sample. The method includes receiving a digital image of a tissue sample identifying the number and location of A-type cells and B-type cells, obtaining an observed relative distribution, obtaining a reference relative distribution of expected distances between reference A-type cells and reference B-type cells, computing a proximity score as a difference of the reference relative distribution and the observed relative distribution, computing a combined score comprising the proximity score and the density of the A-type cells and/or the density of the B-type cells, and using the combined score for determining the biomedical state of the tissue sample and/or outputting the combined score.

Abstract: The disclosure relates generally to methods for measuring bacteria in biological samples. More particularly, the disclosure relates to methods for measuring bacteria using an aqueous clearance solution.

Abstract: A first projection device includes a first laser projector and a first measurement system. A second projection device includes a second laser projector and a second measurement system. The first projection device and the second projection device is interconnected with a controller. The controller is programmed with computer aided design data representative of a large scale work area and coordinates electronic interaction between the first projection device and the second projection device. The first projection device projects a first indicia that is detectable by the second measurement system and the second projection device projects a second indicia that is detectable by the first measurement system. The controller is adapted for determining relative position within three-dimensional coordinate system of the first projection device to the second projection device from the first indicia detected by the second measurement system and the second indicia detected by the first measurement system.

Abstract: A system for slide marking technique for target tissue extraction and downstream application includes at least a marking device configured to receive a sample associated with a stained slide, to image an unstained surface of the sample associated with the stained slide, and to mark a region of interest on the sample. The system includes at least a computing device comprising at least a processor and a memory, the computing device configured to receive a stained slide image, the computing device configured to receive the image of the unstained surface of the sample, the computing device configured to determine a geometric registration of the unstained surface of the sample to the stained slide image, wherein determining the geometric registration comprises aligning the stained slide image with the image of the unstained surface, the computing device configured to determine the annotation mask as a function of the geometric registration.

Abstract: A method for selecting a final model for detecting cells of interest in image datasets includes dividing a curated image dataset into a training set, a validation set, and a testing set where each image in the curated image dataset has been labeled as positive or negative for a cell of interest. The method trains each model of an ensemble of neural networks using the training and validation sets. Next, each model of the ensemble is tested using the testing set and the predictions of the ensemble are combined. The combined prediction is compared to the label and the method determines whether the combined prediction satisfies a pre-determined level of detection (LOD). If so, the method outputs the ensemble as a final ensemble. If not, the method modifies a hyperparameter of at least one of the models of the ensemble until the combined prediction satisfies the pre-determined LOD.

Abstract: A method for processing one or more histological images captured by a medical imaging device is disclosed. In this method, the histological image is received, and target regions each of which corresponds to a candidate type of tissue are identified based on a predictive model associating one more sample histological images with one or more sample target histological images. One or more display characteristics associated with the identified at least one target histological image is applied to the histological image.

Abstract: A system for color gamut normalization for pathology slide is disclosed. The system includes at least a computing device, wherein the computing device is configured to generate a plurality of segmentations of a whole slide image, wherein the whole slide image includes a plurality of biological tissue type variabilities. The computing device is configured to apply a segment-specific transformation to an individual segment in a first region. The computing device is configured to apply the segment-specific transformation to an individual segment in a second region. The computing device is configured to retrieve a plurality of discrete magnification levels from a user. The computing device is configured to choose as a first magnification level from the plurality of discrete magnification levels, and the computing device is configured to store the plurality of segmentations in a cache.

Abstract: Computer based methods, systems, and computer readable media are provided for intelligently sorting cells using machine learning. A biological cell analysis sorting machine, wherein the biological cell analysis sorting machine comprises a flow cytometry system and a cell analytics sorting system, may be configured to detect configuration issues by analyzing results of a sorting experiment performed by the biological cell analysis sorting machine. An analysis of a history of prior sorting experiments and associated configuration settings may be performed and a corpus of documents pertaining to the sorting experiment based on the detected configuration issues may be analyzed. Updated configuration settings for the biological cell analysis sorting machine based on the performed analysis may be determined, and the biological cell analysis sorting machine may be configured with the updated configuration settings to conduct a desired sorting experiment.

Abstract: Provided is a binarization method for CT sectional image of fiber package containing artifacts, which includes: performing brightness adjustment on the source image obtained after converting of the HSV image model by using a composite tangent function; creating a planar morphological structural element having a morphology similar to that of a target object to obtain a background image without the target object; obtaining a second intermediate image by a subtraction operation of the first intermediate image and the background image; improving an image contrast of the second intermediate image again to obtain a third intermediate image; and binarizing the third intermediate image by using a local adaptive threshold binarization algorithm and removing a background noise to obtain a final binarized image. The binarization method can improve the uneven brightness of the image under complex illumination, alleviate the artifacts, and strip similar objects from the background with similar gray scales.

Abstract: Systems and methods to train a cell object detector are described.

Abstract: An image processing device includes: a processor; and a memory encoded with instructions executed by the processor, including: imaging pluripotent stem cells with time in a culture process and acquiring a plurality of images, extracting a colony region of the cells from the image, extracting a high luminance region on the basis of a group of pixels with larger luminance values than a standard value from among pixels constituting the image, extracting an extraction target region with relatively high contrast in the colony region on the basis of the colony and high luminance regions, and outputting the extraction target region as an extraction result, wherein as a relationship among the colony, high luminance, and extraction target regions, the colony region is formed, the high luminance region is then formed therein, and the extraction target region is then formed in the high luminance region in the culture process of the cells.

Abstract: Systems and methods for denoising a magnetic resonance (MR) image utilize an unsupervised deep convolutional neural network (U-DCNN). Magnetic resonance (MR) image data of an area of interest of a subject can be acquired, which can include noisy input images that comprise noise data and noise free image data. For each of the noisy input images, iterations can be run of a converging sequence in an unsupervised deep convolutional neural network. In each iteration, parameter settings are updated; the parameter settings are used in calculating a series of image feature sets with the U-DCNN. The image feature sets predict an output image. The converging sequence of the U-DCNN is terminated before the feature sets predict a respective output image that replicates all of the noise data from the noisy input image. Based on a selected feature set, a denoised MR image of the area of interest of the subject can be output.