Abstract: Systems and methods are provided for generating clusters of anomalous images. Histopathological samples are images at an associated imaging system to produce a plurality of images. A plurality of anomalous images are identified from the plurality of images at an anomaly detection system, having an associated latent space. The plurality of anomalous images are clustered to generate a plurality of clusters within a feature space defined by a set of classification features. The set of classification features include a feature derived from the latent space associated with the anomaly detection system.

Abstract: A convolutional neural network (CNN) is applied to identifying tumors in a histological image. The CNN has one channel assigned to each of a plurality of tissue classes that are to be identified, there being at least one class for each of non-tumorous and tumorous tissue types. Multi-stage convolution is performed on image patches extracted from the histological image followed by multi-stage transpose convolution to recover a layer matched in size to the input image patch. The output image patch thus has a one-to-one pixel-to-pixel correspondence with the input image patch such that each pixel in the output image patch has assigned to it one of the multiple available classes. The output image patches are then assembled into a probability map that can be co-rendered with the histological image either alongside it or over it as an overlay. The probability map can then be stored linked to the histological image.

Abstract: Systems and methods are provided for generating clusters of anomalous images. Histopathological samples are images at an associated imaging system to produce a plurality of images. A plurality of anomalous images are identified from the plurality of images at an anomaly detection system, having an associated latent space. The plurality of anomalous images are clustered to generate a plurality of clusters within a feature space defined by a set of classification features. The set of classification features include a feature derived from the latent space associated with the anomaly detection system.

Abstract: Systems and methods are provided for screening histopathology tissue samples. An anomaly detection system is trained on a plurality of training images. Each of the plurality of training images represents a tissue sample that is substantially free of abnormalities. A test image, representing a tissue sample, is provided to the anomaly detection system. A deviation from normal score is generated for at least a portion of the test image. The deviation from normal score represents a degree of abnormality in the tissue sample represented by the test image.

Abstract: Systems and methods are provided for screening a set of histopathology tissue samples representing a region of interest for abnormalities. A pattern recognition classifier is trained on a first set of images, each representing a tissue sample that is substantially free of abnormalities, and a second set of images, each representing one of the set of histopathology tissue samples representing the region of interest. At least one performance metric from the pattern recognition classifier is generated. A given performance metric represents one of an accuracy of the classifier in discriminating between images representing tissue that is substantially free of abnormalities and images of histopathology tissue samples representing the region of interest and a training rate of the pattern recognition classifier. A likelihood of abnormalities in the region of interest is determined from the at least one performance metric from the pattern recognition classifier.

Abstract: A convolutional neural network (CNN) is applied to identifying tumors in a histological image. The CNN has one channel assigned to each of a plurality of tissue classes that are to be identified, there being at least one class for each of non-tumorous and tumorous tissue types. Multi-stage convolution is performed on image patches extracted from the histological image followed by multi-stage transpose convolution to recover a layer matched in size to the input image patch. The output image patch thus has a one-to-one pixel-to-pixel correspondence with the input image patch such that each pixel in the output image patch has assigned to it one of the multiple available classes. The output image patches are then assembled into a probability map that can be co-rendered with the histological image either alongside it or over it as an overlay. The probability map can then be stored linked to the histological image.

Abstract: A convolutional neural network (CNN) is applied to identifying tumors in a histological image. The CNN has one channel assigned to each of a plurality of tissue classes that are to be identified, there being at least one class for each of non-tumorous and tumorous tissue types. Multi-stage convolution is performed on image patches extracted from the histological image followed by multi-stage transpose convolution to recover a layer matched in size to the input image patch. The output image patch thus has a one-to-one pixel-to-pixel correspondence with the input image patch such that each pixel in the output image patch has assigned to it one of the multiple available classes. The output image patches are then assembled into a probability map that can be co-rendered with the histological image either alongside it or over it as an overlay. The probability map can then be stored linked to the histological image.

Abstract: A convolutional neural network (CNN) is applied to identifying tumors in a histological image. The CNN has one channel assigned to each of a plurality of tissue classes that are to be identified, there being at least one class for each of non-tumorous and tumorous tissue types. Multi-stage convolution is performed on image patches extracted from the histological image followed by multi-stage transpose convolution to recover a layer matched in size to the input image patch. The output image patch thus has a one-to-one pixel-to-pixel correspondence with the input image patch such that each pixel in the output image patch has assigned to it one of the multiple available classes. The output image patches are then assembled into a probability map that can be co-rendered with the histological image either alongside it or over it as an overlay. The probability map can then be stored linked to the histological image.

Abstract: Systems and methods are provided for screening histopathology tissue samples. An anomaly detection system is trained on a plurality of training images. Each of the plurality of training images represents a tissue sample that is substantially free of abnormalities. A test image, representing a tissue sample, is provided to the anomaly detection system. A deviation from normal score is generated for at least a portion of the test image. The deviation from normal score represents a degree of abnormality in the tissue sample represented by the test image.

Abstract: The present invention provides methods and systems for automatic detection of the location of cell colonies on a specimen slide, in particular under the coverslip of a specimen slide. Slide scanning can be performed using an automated microscope with motorized axes. The location of the colonies can be determined by image analysis, which is followed by automatically finding metaphase cells and associating them with each colony. The invention also provides an automated, Hough-transform-based method for identifying the location of the slide coverslip and, if desired, analyzing only the image area contained within the coverslip.

Abstract: The present invention provides methods and systems for automatic detection of the location of cell colonies on a specimen slide, in particular under the coverslip of a specimen slide. Slide scanning can be performed using an automated microscope with motorized axes. The location of the colonies can be determined by image analysis, which is followed by automatically finding metaphase cells and associating them with each colony. The invention also provides an automated, Hough-transform-based method for identifying the location of the slide coverslip and, if desired, analyzing only the image area contained within the coverslip.

Abstract: Scanning and analysis of cytology and histology samples uses a flatbed scanner to capture images of the structures of interest such as tumor cells in a manner that results in sufficient image resolution to allow for the analysis of such common pathology staining techniques as ICC (immunocytochemistry), IHC (immunohistochemistry) or in situ hybridization. Very large volumes of such material are scanned in order to identify cells or clusters of cells which are positive or warrant more detailed examination, and if analysis at higher resolution is necessary, information regarding these positive events is transferred to a secondary microscope, such as a conventional scanning microscope, to allow further analysis and review of the selected regions of the slide containing the sample.

Abstract: Scanning and analysis of cytology and histology samples uses a flatbed scanner to capture images of the structures of interest such as tumor cells in a manner that results in sufficient image resolution to allow for the analysis of such common pathology staining techniques as ICC (immunocytochemistry), IHC (immunohistochemistry) or in situ hybridization. Very large volumes of such material are scanned in order to identify cells or clusters of cells which are positive or warrant more detailed examination, and if analysis at higher resolution is necessary, information regarding these positive events is transferred to a secondary microscope, such as a conventional scanning microscope, to allow further analysis and review of the selected regions of the slide containing the sample.