Abstract: An image processing device for processing a stained sample image including hematoxylin stain is provided with a dye spectrum storage unit that stores a dye spectrum of dye used in staining, a change characteristic calculation unit that calculates a change characteristic in a wavelength direction of the dye spectrum based on the dye spectrum, a dye amount/wavelength shift amount estimation unit that estimates at least a dye amount of the hematoxylin stain and a shift amount in the wavelength direction for each pixel in the stained sample image based on the dye spectrum and the change characteristic; and a cell nucleus extraction unit that extracts a cell nucleus region of the stained sample image based on the shift amount estimated in the wavelength direction.

Abstract: A method and system for setting image analysis parameters to control image analysis operations. The method and system include collecting set of digital training images including a set of states for the set of digital training images. An objective function is defined to determine a relative quality of plural different parameter sets used for digital image analysis. Values for the plural different parameter sets that maximize (or minimize) the objective function are determined. The method and system increases a usability of high content screening technologies by reducing a required level of expertise required to configure digital image processing.

Abstract: A medical image processing apparatus includes a vessel running data generating unit, a lesion site detecting unit, a vessel dominant region data generating unit, a lesion site dominant region data generating unit, and a diagnostic image data generating unit. The vessel running data generating unit generates vessel running data of a vessel. The lesion site detecting unit detects positional information of a lesion site in the vessel. The vessel dominant region data generating unit generates vessel dominant region data indicating a region dominated by the vessel in a region provided with nutrition. The lesion site dominant region data generating unit generates lesion site dominant region data indicating a region dominated by the lesion site in the region provided with nutrition. The diagnostic image data generating unit generates diagnostic image data by superimposing the vessel dominant region data and the lesion site dominant region data on morphological image data.

Abstract: Embodiments herein provide methods for noninvasive assessment of keratinocytes. Digital imaging and processing of gray-levels are used to identify cells. More specifically, embodiments provide an automated algorithm that may be used to identify keratinocytes, and/or to specify the coordinates/locations of keratinocytes, through noninvasive confocal imaging.

Abstract: Methods of identifying microRNA labeled with a fluorescent probe in a biological sample are disclosed. The methods include obtaining a plurality of fluorescence images of the sample and forming an image stack based on the plurality of fluorescence images, decomposing the image stack to obtain a component image that corresponds to the labeled microRNA, and identifying the microRNA based on the component image.

Abstract: A support system for histopathological diagnosis includes a cell nucleus uniformity evaluation unit evaluating a uniformity of a plurality of cell nuclei included in a ductal region in an image. With this configuration, there is provided a support system, a support method and a support program for histopathological diagnosis, which enables realization of highly accurate cancer differentiation in a pathological diagnosis.

Abstract: In accordance with the principles of the invention, methods, systems, and computer-readable mediums are provided for positioning cellular analysis data including measuring a similarity between pixel data in a target sample data and pixel data in a template data. An offset position is determined based on the measured similarity. The pixel data in the template data is shifted based on the offset position to produce shifted template data having pixel data at shifted locations which match the corresponding pixel data in the target sample data.

Abstract: A method for automatically rapidly analyzing biological cells includes continuously capturing a plurality of image frames of a suspension including a plurality of biological cells according to a predetermined time interval within a predetermined time using a low-magnification optical image amplification device of a image capture device; transmitting each of the plurality of image frames to an operation processing device; the operation processing device utilizing an image identification technology to detect a number of the plurality of biological cells in an image frame and a static data of each biological cell of the plurality of biological cells according to at least one parameter; and the operation processing device generating a dynamic data of each biological cell in the image frame according to the static data of each biological cell in the image frame and the static data of each biological cell of a previous image frame.

Abstract: A method for generating a brightfield type image, which resembles a brightfield staining protocol of a biological sample, using fluorescent images is provided. The steps comprise acquiring two or more fluorescent images of a fixed area on a biological sample, mapping said fluorescent image into a brightfield color space, generating a brightfield image, and optionally applying a sharpening transformation correction. Also provided is an image analysis system for generating a brightfield type image of a biological sample using fluorescent images.

Abstract: A system for performing high-speed, high-resolution imaging cytometry utilizes a line-scan sensor. A cell to be characterized is transported past a scan region. An optical system focuses an image of a portion of the scan region onto at least one linear light sensor, and repeated readings of light falling on the sensor are taken while a cell is transported though the scan region. The system may image cells directly, or may excite fluorescence in the cells and image the resulting light emitted from the cell by fluorescence. The system may provide a narrow band of illumination at the scan region. The system may include various filters and imaging optics that enable simultaneous multicolor fluorescence imaging cytometry. Multiple linear sensors may be provided, and images gathered by the individual sensors may be combined to construct an image having improved signal-to-noise characteristics.

Abstract: In a device and associated method to extract a tissue sample, spatial coordinates of tissue variations in slice images are determined and tested by a forward projection in projection images in order, with tested spatial coordinates, to create revised slice images with a precise localization of a tissue variation.

Abstract: Embodiments of the disclosure are directed to segmenting a digital image of biological tissue into biological units, such as cells. A first weak or data driven segmentation is generated using image data representing the digital image to segment the digital image into a first set of biological units. Applying a geometric model, each unit in the first set of biological units is ranked based on a similarity in shape and scale between the unit and one or more other units in the image. A subset of units from the first set of biological units is selected based on the rank of each biological unit relative to a predetermined threshold rank. A second weak or data driven segmentation may then be generated using image data including the subset of biological units to segment that portion of the digital image into a second set of biological units.

Abstract: A method or apparatus for stain separation comprising transforming a digital image from a first color domain to an optical domain to form an optical domain image (ODI), identifying a plane containing two or more basis vector which contain the pixels of the ODI, determining a plurality of orthogonal vector within the identified plane, forming a histogram of the digital image represented by the orthogonal vectors and determining one or more final stain vectors by searching for candidate vectors in the plane that minimize a cost function of the histogram.

Abstract: A computer-implemented method and apparatus for stain separation of a pathology image using stain vector analysis comprising converting an original image into an optical domain image, performing stain vector analysis on the optical domain image to obtain one or more stain vectors, deconvoluting the vectors adaptively to produce one or more separated stain images.

Abstract: A system and method for improved detection of objects of interest in image data using adaptive stepwise classification and hierarchical decision diagrams to manage false positives is provided. The present invention uses an adaptive stepwise classification approach, preferably based on a hierarchical binary decision diagram (BDD), to enable the efficient management of false positive objects to improve detection performance. The present invention is particularly suited for the reduction of false positives during the detection of acid fast bacilli associated with tuberculosis.

Abstract: Provided herein are systems methods including a design of a microscope slide scanner for digital pathology applications which provides high quality images and automated batch-mode operation at low cost. The instrument architecture is advantageously based on a convergence of high performance, yet low cost, computing technologies, interfaces and software standards to enable high quality digital microscopy at very low cost. Also provided is a method based in part on a stitching method that allows for dividing an image into a number of overlapping tiles and reconstituting the image with a magnification without substantial loss of accuracy. A scanner is employed in capturing snapshot images. The method allows for overlapping images captured in consecutive snapshots.

Abstract: Exemplary embodiments enable determination of spatial proximity between two or more features in biological tissue. An exemplary method includes identifying a morphological feature in an image of the biological tissue based on expression levels of a first biomarker indicative of the morphological feature, and receiving a result of a segmentation analysis performed on the image of the biological tissue identifying a set of morphological units in the image external to the morphological feature. An exemplary method includes determining an expression level of a second biomarker corresponding to each unit in the set of morphological units in the image of the biological tissue, and determining a spatial distance between the morphological feature and each unit in the set of morphological units.

Abstract: The invention relates to a general composite compartmental model and a compartmental analysis procedure to extract non-invasively the concentration (Cp) of the imaging agent in plasma (301), in metabolites (304, 504) and in blood elements (303) (like red cells, platelets, plasma protein etc.) from time signal curves measured within a reference tissue region (200). This is made possible by deploying an injection function (SINJ(t)) as input which models the amount of imaging agent administered to the patient as a function of time. The invention allows the presentation of the plasma input function to the medical practitioner without the need for invasively drawing blood samples.

Abstract: The invention generally relates to analytical and monitoring systems useful for analyzing and measuring cells and biological samples. More particularly, the invention provides systems and methods for internal calibration and focus reference for cytometry imaging.

Abstract: An apparatus and method for image normalization using a Gaussian residual of fit selection criteria. The method may include acquiring a two-dimensional image of a plurality of particles, where the plurality of particles comprises a plurality of calibration particles, and identifying a calibration particle by correlating a portion of the image corresponding to the calibration particle to a mathematical model (e.g. Gaussian fit). The measured intensity of the calibration particle may then be used to normalize the intensity of the image.

Abstract: This invention relates to algorithms, methods and products useful in assessing steatosis level of tissues, using an automated high-content image analysis framework. The algorithms, methods and products are particularly useful in liver transplantation by providing a fast, precise and reproducible steatosis level estimation pre-transplantation. The invention also enables in vitro high throughput screening of drug candidates for reducing intra-cellular triglyceride content in the form of lipid droplets from fatty livers.

Abstract: Embodiments provide a Magnetic Resonance Imaging (MRI) technique and optionally software—collectively referred to as the “shutter-speed” model—to analyze image data of cancer patients. Embodiments provide a minimally invasive, yet precisely accurate, approach to determining whether tumors are malignant or benign by distinguishing the characteristics of contrast reagent activity in benign and malignant tumors. Exemplary embodiments provide MRI measured biomarkers for tumor malignancy determination, effectively eliminating or limiting the false positives suffered by existing MRI techniques.

Abstract: A system and method for automatically and quantitatively determining the optimal dilution of a reagent is provided. In one embodiment, a plurality of dilution sets are received, where each of the dilution sets consist of a different respective dilution value and a respective plurality of immunoassay staining intensity values. A respective dynamic range metric is determining for each of the plurality of dilution sets relative to the respective plurality immunoassay staining intensity values. Having found the respective dynamic range metric, a dilution set having the numerically optimal dynamic range metric is selected and the dilution value of that dilution set is selected as being representative of an optimal dilution level of the reagent for use in a quantitative immunoassay. In one embodiment, a system is provided with a microscope, an image sensor, and processor module configured determine an optimal dilution of a reagent for use in an quantitative immunoassay.

Abstract: A method for determining radiation exposure from chromosome abnormalities present in a specimen by determining the location or locations of the centromere of each chromosome in a cell in an image of a metaphase cell by segmentation of an accurately drawn chromosome centerline followed by selection of a longitudinal cross-section with the minimum width or intensity or width and intensity; counting the number of centromeres in each chromosome in each cell; computing the frequency of dicentric chromosomes in a population of cells; and determining the radiation dose by comparing the computed frequency of dicentric chromosomes with a previously determined dose-response curve from a calibrated source.

Abstract: An information processing apparatus, which creates a tree structure used by a recognition apparatus which recognizes specific information using the tree structure, including a memory unit which stores data including the information to be recognized and data not including the information so as to correspond to a label showing whether or not the data includes the information, a recognition device which recognizes the information and outputs a high score value when the data including the information is input, and a grouping unit which performs grouping of the recognition devices using a score distribution obtained when the data is input into the recognition devices.

Abstract: A method of processing data associated with fluorescent emissions from a microfluidic device. The method includes performing an auto-focus process associated with a first image of the microfluidic device and performing an auto-exposure process associated with the first image of the microfluidic device. The method also includes capturing a plurality of images of the microfluidic device. The plurality of images are associated with a plurality of thermal cycles. The method further includes performing image analysis of the plurality of captured images to determine a series of optical intensities and performing data analysis of the series of optical intensities to provide a series of change in threshold values.

Abstract: A new morphological feature referred to herein as profile weighted intensity feature is provided, useful for automated classification of objects, such as cells, that are depicted in digital images. In certain embodiments, the profile weighted intensity feature is determined by automatically identifying a border of a cell in an input image, determining a distance image for the cell, computing a profile function for the cell, and computing a mean intensity of at least a portion of the input image weighted by the profile function for the cell.

Abstract: Various embodiments of the present invention provide methods and systems for optimally staining biological samples for analysis. In one embodiment, images of a sample are recorded before and after the application of a staining reagent and a decolorization reagent. A difference image is then generated based at least in part on a comparison of the images of the sample recorded before and after the application of the staining and decolorization reagents. Application parameters of the staining and decolorization reagents are then corrected based at least in part on the difference image such that the reagents may be optimally reapplied to generate a final image of the sample that may enable a user to better differentiate at least one target of interest in the sample. In one example, embodiments of the present invention allow for the generation of images that show only Gram-positive bacteria or only Gram-negative bacteria.

Abstract: The present invention may include segmenting an image at a first resolution level and a second resolution level, wherein one or more parameters of a segmentation algorithm are trainable via user classification feedback, extracting features from a first plurality of segment primitives and a second plurality of segment primitives, wherein one or more parameters of a segment feature extraction algorithm are trainable via user classification feedback, building a first and second segmentation hierarchy by generating one or more clusters of the first plurality of segment primitives and the second plurality of segment primitives, extracting one or more features from the first segmentation hierarchy and the second segmentation hierarchy utilizing a hierarchy feature extraction algorithm, determining an inter-level relationship between the clusters generated for the first resolution level and the second level, and automatically classifying one or more tissue elements of the tissue specimen via a user-trained classific

Abstract: Disclosed is a computer implemented method for fully automated tissue diagnosis that trains a region of interest (ROI) classifier in a supervised manner, wherein labels are given only at a tissue level, the training using a multiple-instance learning variant of backpropagation, and trains a tissue classifier that uses the output of the ROI classifier. For a given tissue, the method finds ROIs, extracts feature vectors in each ROI, applies the ROI classifier to each feature vector thereby obtaining a set of probabilities, provides the probabilities to the tissue classifier and outputs a final diagnosis for the whole tissue.

Abstract: A data processing system receives an image of a matrix including a plurality of living cells. The data processing system automatically locates a cell among the plurality of living cells in the image by performing image processing on the image. In response to locating the cell, the data processing system records, in data storage, a position of the cell in the image. The data processing system may further automatically determine, based on the image, one or more selected metrics for the cell, such as one or more motility metrics, one or more frequency metrics and/or one or more morphology metrics. Based on the one or more metrics, the data processing system may further automatically determine a probability of success of a therapy on a patient employing a test substance and/or automatically select a treatment plan for recommendation.

Abstract: This invention is directed to improvement of the accuracy of cancer differentiation in the pathologic diagnosis using a pathologic tissue image analysis. There are included a stroma area/duct area detecting module for detecting, from a biological tissue image, a duct area on the basis of duct characteristic information indicating the characteristic of ducts included in a tissue area in the biological tissue image; an intraduct cell-nucleus detecting module for extracting, based on a predetermined pigment reference, cell nucleuses included in the detected duct area; and a duct formation evaluating module for calculating a heterotypic degree of each duct on the basis of the distribution state of the cell nucleuses for a predetermined base areas in each duct.

Abstract: Pathologic tissue images are to be output which allow effective image diagnosis to be performed. There are included an index amount calculating unit that divides a captured pathologic image into a predetermined divisional areas and sets a measurement index value related to a reference of pathologic diagnosis for each divisional area; and a significance calculating module that sets, for each divisional area, a significance related to the pathologic measurement on the basis of both the measurement index value of each divisional area and the measurement index value of a respective divisional area adjacent to that divisional area. The significance calculating module extracts that one of the divisional areas in which the areas for which images of the living tissues have been captured represent a given percentage, and further the significance calculating module associates, with the extracted divisional area, the measurement index value and significance set therefor for transmission.

Abstract: An image processing program (GP) attains (S10) time lapse images, extracts (S20) a cell aggregation from each of the obtained images, and calculates (S50), for the entire region of the cell aggregation, the spatial distribution in pixel values and temporal change in pixel values of a small region in the extracted cell aggregation. The program determines (S70) the state of change of the cell aggregation toward becoming multi-layered, on the basis of the calculated spatial distribution and time lapse change of pixel values, and outputs (S80) the results of the determination. The image processing program (GP) is configured so as to determine and output, from time lapse images, the state of change of the cell aggregation toward becoming multi-layered.

Abstract: Statistical data of a fluorescence population is obtained easily with high accuracy. To achieve this, an evaluation apparatus of fluorescence population of the present application includes an input unit inputting a fluorescence observation image (If) of a fluorescence population and a transillumination observation image (It) having a same field of view as the fluorescence observation image, a first detecting unit (Mt) detecting, as a first area, an area in which a cellular image exists on the transillumination observation image being input, a setting unit (If?) setting, as a reference area, an area corresponding to the first area on the fluorescence observation image being input, and an obtaining unit obtaining fluorescence intensity data of a fluorescence image from the reference area in the fluorescence observation image.

Abstract: This invention, which provides a method for detecting a corruption in an image acquired from a biological sample, includes: providing at least one image of at least one cell; generating the image of the at least one cell over a period of time; determining if the at least one image of the at least one cell is corrupted; applying a wavelet transform, Fourier transform, or other frequency decomposing transform to the at least one image to decompose the at least one image into a plurality of sub-images, wherein the plurality of sub-images have a plurality of low frequency channels, a plurality of middle frequency channels and a plurality of high frequency channels; calculating a ratio based on an energy level of the plurality of low frequency channels and the plurality of middle frequency channels; and removing the at least one image of at least one cell if the at least one image is corrupted.

Abstract: This disclosure is directed to imaging techniques and image analysis techniques for automated analysis of biological growth media. According to this disclosure, the spectral responses of biological growth media can be used to identify and count biological agents from images of biological growth media. The biological growth media may be illuminated with two or more different wavelengths of electromagnetic radiation, and images of the biological growth media can be captured under these different illuminations. The spectral reflectance values in one or more first images can be normalized based on the spectral reflectance values in one or more second images, wherein the first images are associated with a different wavelength of illumination than the second images. The normalization may allow for better identification of biological agents that manifest on the biological growth media.

Abstract: In a tracing mode of an electronic endoscope system, a target designating frame is displayed on a monitor to enable designating a tracing target in an endoscopic image captured from an interior of a body cavity illuminated with a broadband light. After the tracing target is designated, narrowband rays of different wavelength ranges from each other are sequentially projected into the body cavity, to acquire biological information on the designated tracing target from image signals obtained under these narrowband rays. On the basis of the biological information on the tracing target, an area corresponding to the tracing target is detected from endoscopic images newly captured after the designation of the tracing target.

Abstract: This invention relates to an information processing apparatus which assists diagnosis based on a tissue sample image obtained by staining and capturing a tissue. The information processing apparatus receives and analyzes lower magnification image data among a plurality of image data obtained at different magnifications for an area image selected in the tissue sample image. Based on the analysis result, the information processing apparatus determines whether analysis based on higher magnification image data is necessary. When analysis based on the higher magnification image data is necessary, the information processing apparatus notifies a request of transmitting the higher magnification image data for the area image, receives and analyzes the higher magnification image data transmitted in response to the transmission request, and transmits the analysis result.

Abstract: Methods for chromogen separation-based image analysis are provided, with such methods being directed to quantitative video-microscopy techniques in cellular biology and pathology applications.

Abstract: Methods and systems for image scoring and analysis are provided. Scored and analyzed images may include digital pathology images. Image scoring and analysis methods may include techniques to identify nuclei and determine membrane staining extent through the use of a priori models. Image scoring and analysis methods may include techniques for membrane intensity determination. Images may be scored based on an extent of membrane staining and membrane intensity.

Abstract: A method of segmenting biological cells in a picture so that the biological cells represent a foreground of the picture includes a step of applying a first fast marching algorithm to the picture or to a pre-processed version of same in order to obtain a first fast marching image. In addition, the method includes a step of segmenting the first fast marching image or a further-processed version of same into a plurality of homogeneous regions. Furthermore, the method includes a step of mapping each of the homogeneous regions to one node of a graph, respectively. In addition, the method includes a step of classifying each homogeneous region either as background or foreground on the basis of the graph. Moreover, the method includes a step of applying a second fast marching algorithm within the homogeneous regions classified as foreground so as to segment the foreground into individual biological cells.

Abstract: A detector and method for automatically detecting signet ring cells in an image of a biopsy tissue sample, includes finding in the image, points about which cell membranes appear in radial symmetry; selecting as candidate points, at least ones of the points that have an adjacent nuclei with a predetermined shape feature; and applying a convolutional neural network to the candidate points to determine which of the candidate points are signet ring cells.

Abstract: Virtual slide image data and corresponding information are stored in a data storage area on a virtual slide image server. A client viewer requests image data at a particular resolution. The image server obtains corresponding image data from the data storage area at a resolution nearest to the requested resolution. The image data is then sent to the client viewer. The client viewer receives the image data and scales the image data to the requested resolution prior to displaying the image data.

Abstract: Disclosed is an imaging system that stores and retrieves very large scanned digital images, as in applications that automatically scan biological samples using a computer-controlled digital camera microscope. Slide data is entered, zelle data is captured and compressed and a zelle database file is loaded. Furthermore, an image database file is loaded and it is determined whether another zelle is to be stored. The image can be retrieved by accessing the zelle database, reading a zelle record, reading an image file, loading the display buffer, and determining whether another zelle is to be loaded.

Abstract: An ophthalmology apparatus may be provided with an input device, a processor, and an output device. The input device may be configured to input a corneal endothelial cell image to the processor. The corneal endothelial cell image can be obtained by photographing a corneal endothelial cell. The processor may be configured to extract a dark area from the corneal endothelial cell image input by the input device, and to analyze the extracted dark area. The output device may output a result of the analysis by the processor.

Abstract: The present techniques provide for the evaluation of cellular motion and/or cellular properties based on an analysis of motion for cluster of cells. In an exemplary technique, images of cells are acquired and the image is segmented into clusters. Motion data for each respective cluster is derived from the segmented data. The properties of each cluster can be used to evaluate cellular properties and/or cellular motion properties.

Abstract: Determining at least one of a prognosis or a therapy for a patient based on a stained tissue section of the patient. An image of a stained tissue section of a patient is processed by a processing device. A set of features values for a set of cell-based features is extracted from the processed image, and the processed image is associated with a particular cluster of a plurality of clusters based on the set of feature values, where the plurality of clusters is defined with respect to a feature space corresponding to the set of features.

Abstract: The invention provides a reconfigurable module allowing morphological operations to be carried out for image processing. The module includes an operational block having five inputs, three outputs, three adders/subtracters and four logic blocks. The logic blocks provide various routings between the three adders/subtracters to enable the outputs to deliver the result of basic operations carried out on the five inputs. The reconfigurable module has a reduced number of components while at the same time allowing various morphological operations to be performed whose parameters can be modified. Furthermore, the reconfigurable module is serially combined to carry out more complex morphological operations. The invention also provides a method for implementing the reconfigurable module allowing an integral image, an eroded image, an expanded image, a distance image or projections along the rows and columns of the original image to be determined starting from an original image.

Abstract: A computer-implemented method of imaging an assay sample having a set of individual samples using a camera is provided. A set of image frames is received. The set of image frames corresponds to an image stream of the assay obtained by the camera. A set of measurement results is identified. Individual measurement results in the set of measurement results are respectively associated with individual image frames in the set of image frames. A subset of measurement results is selected based, at least in part, on an exposure time. Individual measurement results in the subset of measurement results are combined to obtain an integrated measurement result.