Abstract: Aspects relate to reconstructing phase images from brightfield images at multiple focal planes using machine learning techniques. A machine learning model may be trained using a training data set comprised of matched sets of images, each matched set of images comprising a plurality of brightfield images at different focal planes and, optionally, a corresponding ground truth phase image. An initial training data set may include images selected based on image views of a specimen that are substantially free of undesired visual artifacts such as dust. The brightfield images of the training data set can then be modified based on simulating at least one visual artifact, generating an enhanced training data set for use in training the model. Output of the machine learning model may be compared to the ground truth phase images to train the model. The trained model may be used to generate phase images from input data sets.

Abstract: Certain configurations are described of methods and systems that can be used to image three-dimensional objects such as biological cells, biological tissues or biological organisms. The methods and systems can image the three-dimensional objects at reduced imaging times and with reduced data volumes.

Abstract: Presented herein are systems and methods for registering one or more images of one or more subjects based on the automated generation of artificial landmarks. An artificial landmark is a point within an image that is associated with a specific physical location of the imaged region. The artificial landmarks are generated in an automated and robust fashion along the bones of a subject's skeleton that are represented in the image (e.g. graphically). The automatically generated artificial landmarks are used to correct distortion in a single image or to correct distortion in and/or co-register multiple images of a series of images (e.g. recorded at different time points). The artificial landmark generation approach described herein thereby facilitates analysis of images used, for example, for monitoring the progression of diseases such as pulmonary diseases.

Abstract: Described herein are computationally efficient systems and methods for processing and analyzing two-dimensional (2D) and three-dimensional (3D) images using texture filters that are based on the Hessian eigenvalues (e.g., eigenvalues of a square matrix of second-order partial derivatives) of each pixel or voxel. The original image may be a single image or a set of multiple images. In certain embodiments, the filtered images are used to calculate texture feature values for objects such as cells identified in the image. Once objects are identified, the filtered images can be used to classify the objects, for image segmentation, and/or to quantify the objects (e.g., via regression).

Abstract: Certain configurations are described of methods and systems that can be used to image three-dimensional objects such as biological cells, biological tissues or biological organisms. The methods and systems can image the three-dimensional objects at reduced imaging times and with reduced data volumes.

Abstract: Provided herein is a method for determining the number of sites of infection of a cell culture, including the steps of: infecting a cell culture arranged in a sample carrier with viruses, counting any infected areas of the cell culture by means of a transmitted light method, marking infected cells with fluorescence markers, counting infected areas of the cell culture by means of a fluorescence analysis method, and evaluating area by area the areas determined in both methods for determining the number of sites of infection.

Abstract: A method for autofocusing a microscope at a correct autofocus position in a sample includes the steps: generating a reference pattern by an autofocus light device, projecting the reference pattern towards a sample, whereby the reference pattern is backscattered by at least two interfaces being located at or close to the sample, projecting the backscattered reference pattern towards a detector which provides spatial resolution, obtaining a superposition of a number of detection patterns, each detection pattern related to one of the interfaces, on the detector, analyzing the superposition of detection patterns to identify at least one autofocus detection pattern related to at least one of the interfaces, and analyzing the at least one autofocus detection pattern to determine the direction and/or magnitude of deviation of the microscope's current focus position from the correct focus position.

Abstract: Presented herein, in certain embodiments, are approaches for robust bone splitting and segmentation in the context of small animal imaging, for example, microCT imaging. In certain embodiments, a method for calculating and applying single and hybrid second-derivative splitting filters to gray-scale images and binary bone masks is described. These filters can accurately identify the split lines/planes of the bones even for low-resolution data, and hence accurately morphologically disconnect the individual bones. The split bones can then be used as seeds in region growing techniques such as marker-controlled watershed segmentation. With this approach, the bones can be segmented with much higher robustness and accuracy compared to prior art methods.

Abstract: Described herein is a method for adjusting one or more images of a sample to correct geometric distortions and/or to properly align the one or more images using a pattern of dots, e.g., a quasiperiodic grid.

Abstract: An apparatus for structured illumination of a specimen comprises an illumination device for generating illumination beams. The illumination beams are incident on a mask device. Openings provided in the mask device serve for generating a mask image. The mask image is imaged within the specimen with the aid of an objective. Detection beams generated by the specimen are captured by a detection device. For increasing the intensity of the observation beams entering the specimen, those beams which do not pass through the openings, are collected with the aid of a beam collector and guided back to the mask device.

Abstract: An apparatus for confocal observation of a specimen includes an illumination device. The illumination device generates illumination radiations of at least two different wavelengths. With the aid of a mask device illuminated by the illumination radiations, one mask image is generated per wavelength. An objective serves for imaging said mask images in the specimen. With the aid of a beam splitter device, the emission radiations emitted by the specimen are divided based on the wavelengths, and are detected based on the wavelengths by a detection device.

Abstract: Described herein is a method for adjusting one or more images of a sample to correct geometric distortions and/or to properly align the one or more images using a pattern of dots, e.g., a quasiperiodic grid.

Abstract: Disclosed are methods for analyzing the effect of a test substance on biological and/or biochemical samples in which a plurality of samples, each comprising a known concentration of the test substance in at least three different concentrations, are used to obtain measurements which provide raw data. An evaluation rule utilizes the raw data of the sample determining the effect of the test substance, at the particular concentration, on the sample. The evaluation rule is influenced by at least one control parameter, and at least one starting value for the at least one control parameter is determined. The raw data is evaluated and correspondence between the determined activities and a functional model resulting from theoretical considerations yields a dose/effect curve describing the dependence of the activities on the concentration of the test substance. The steps are modified and repeated until an abort criterion has been reached.

Abstract: A new family of morphological features, referred to herein as threshold compactness features, is provided, useful for automated classification of objects, such as cells, in images. In one embodiment, one or more thresholds and/or binary masks are applied to an image, and one or more provisional objects within a cell in the image are automatically identified. The threshold compactness of the cell is computed as a function of area S of the one or more provisional objects and border length P of the one or more provisional objects. Computation of threshold compactness allows cells in an image to be distinguished and characterized. Compared to previous techniques, the methods and apparatus described herein are more robust and computationally efficient.

Abstract: Described herein are systems and methods for efficient and accurate, automated detection of a region of interest interior to the ribcage from an in vivo mammalian image. It is found that efficient, automated identification of the region of interest interior to the ribcage can be achieved by the use of both a bone distance mask and a surface distance mask. The technique solves the problem of accurate and fast identification of the region of interest for a wide range of sizes and shapes of mammals, e.g., small mammals such as mice.

Abstract: Methods and devices for the separation of particles (20, 21, 22) in a compartment (30) of a fluidic microsystem (100) are described, in which the movement of a liquid (10) in which particles (20, 21, 22) are suspended with a predetermined direction of flow through the compartment (30), and the generation of a deflecting potential in which at least a part of the particles (20, 21, 22) is moved relative to the liquid in a direction of deflection are envisaged, whereby further at least one focusing potential is generated, so that at least a part of the particles is moved opposite to the direction of deflection relative to the liquid by dielectrophoresis under the effect of high-frequency electrical fields, and guiding of particles with different electrical, magnetic or geometric properties into different flow areas (11, 12) in the liquid takes place.

Abstract: Described herein are systems and methods for efficient and accurate, automated detection of a region of interest interior to the ribcage from an in vivo mammalian image. It is found that efficient, automated identification of the region of interest interior to the ribcage can be achieved by the use of both a bone distance mask and a surface distance mask. The technique solves the problem of accurate and fast identification of the region of interest for a wide range of sizes and shapes of mammals, e.g., small mammals such as mice.

Abstract: In various embodiments, methods and apparatus are provided for automated selection of features of cells useful for classifying cell phenotype. The methods include determining a signal-to-noise ratio (S/N) for each of a plurality of pairs of features, rather than S/N for individual features. The approach is capable of quickly identifying a small set of features of imaged cells that are most relevant for classification of a desired cell phenotype from among a very large number of features. The small group of relevant features can then be used to more efficiently and more accurately classify phenotype of unidentified cells.

Abstract: A new family of morphological features, referred to herein as threshold compactness features, is provided, useful for automated classification of objects, such as cells, in images. In one embodiment, one or more thresholds and/or binary masks are applied to an image, and one or more provisional objects within a cell in the image are automatically identified. The threshold compactness of the cell is computed as a function of area S of the one or more provisional objects and border length P of the one or more provisional objects. Computation of threshold compactness allows cells in an image to be distinguished and characterized. Compared to previous techniques, the methods and apparatus described herein are more robust and computationally efficient.

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.