Abstract: One type of tissue-based assay, the companion diagnostic (“CDx”) allows for the identification of individuals within a larger patient population who are more likely to respond to a therapy. The CDx paradigm typically applies to drugs that target a specific gene product or biologic pathway involving a gene product of interest. It is possible, especially for popular therapeutic targets, for multiple drugs and multiple associated CDx to be developed for a single gene product or biologic pathway involving the gene product. Currently, each of these similar CDx must be applied to identify the best therapy. The present invention can determine the outcome of one CDx using an image of a tissue section used for another CDx. Using a single tissue section and a single CDx, it becomes possible to obtain the outcome of multiple, related CDx.

Abstract: The present invention concerns identifying matching tissue objects in two sections of a tissue block, as imaged using a microscope, for the purpose of mapping the biomarker-specific staining in one section onto the other section. The invention is useful because, in many workflows, it is not possible to add a sufficient number of different biomarker-specific stains to a single slide. By staining instead multiple slides, and mapping the staining data obtained across the slides, one obtains a data set that is similar to what one would be able to obtain by staining a single slide with all those stains. The invention first identifies a set of obviously correct matches, then propagates from those matches, using a priority queue driven process, to optimally match up all fibers in the two sections. The matching is based on the shape and neighborhood configuration of each tissue object.

Abstract: In digital pathology, obtaining a labeled data set for training, testing and/or validation of a machine learning model is expensive, because it requires manual annotations from a pathologist. In some cases, it can be difficult for the pathologist to produce correct annotations. The present invention allows the creation of labeled data sets using fluorescent dyes, which do not affect the appearance of the slide in the brightfield imaging modality. It thus becomes possible to add correct annotations to a brightfield slide without human intervention.

Abstract: One type of tissue-based assay, the companion diagnostic (“CDx”) allows for the identification of individuals within a larger patient population who are more likely to respond to a therapy. The CDx paradigm typically applies to drugs that target a specific gene product or biologic pathway involving a gene product of interest. It is possible, especially for popular therapeutic targets, for multiple drugs and multiple associated CDx to be developed for a single gene product or biologic pathway involving the gene product. Currently, each of these similar CDx must be applied to identify the best therapy. The present invention can determine the outcome of one CDx using an image of a tissue section used for another CDx. Using a single tissue section and a single CDx, it becomes possible to obtain the outcome of multiple, related CDx.

Abstract: The present invention concerns identifying matching tissue objects in two sections of a tissue block, as imaged using a microscope, for the purpose of mapping the biomarker-specific staining in one section onto the other section. The invention is useful because, in many workflows, it is not possible to add a sufficient number of different biomarker-specific stains to a single slide. By staining instead multiple slides, and mapping the staining data obtained across the slides, one obtains a data set that is similar to what one would be able to obtain by staining a single slide with all those stains. The invention first identifies a set of obviously correct matches, then propagates from those matches, using a priority queue driven process, to optimally match up all fibers in the two sections. The matching is based on the shape and neighborhood configuration of each tissue object.

Abstract: We present a method to detect dots in microscope images of tissue samples for the purpose of diagnosis or therapy selection. Dots in tissue arise trough CISH or FISH staining, but also through staining of small cellular compartments, or in other ways. The method is applicable to both brightfield and fluorescence modalities, as well as mass spectrometry imaging methodologies. The method is based on the use of first and second derivatives of the image along the image axes, computed using regularized derivative operators, i.e. Gaussian derivatives. The outputs of these operators are examined at appropriate distances from each location in the image. The found values must have specific signs. If the signs are all correct, these values are multiplied together to obtain a confidence measure for a dot being present at that location. If the signs do not match, no dot is present, and a zero is output.

Abstract: Digital image analysis can simultaneously measure many multidimensional features of each data point within an image. Each data point can then be grouped into categories, or ‘clusters’, of data points by assessing all features of each data point and measuring similarity among all data points. Clustering multidimensional data allows one to visualize the structure of their data and visually represent groups of data points in a lower dimensional space, such as a 2D or 3D graph. If the data points are not tagged with a description before clustering, it is difficult to assess which data points belong to which cluster. In this method, we describe the clustering of tissue objects (data points) into clusters based on their image analysis features, then creating a cluster map in order to describe tissue objects based on cluster association.

Abstract: In accordance with the embodiments herein, a method for displaying differences and similarities between tissue samples utilizing a reference database consisting of tissue images, image analysis features, and derived score from patient tissue samples assayed with a tissue-based test for the purpose of scoring said patient sample and guiding treatment based on said score. The method described herein utilizes digital image analysis of a tissue image of one or more tissue sections to extract features which generates a dataset mathematically representing the image. This dataset is then compared to the reference database to determine reference images with similar and different feature values. Those images are then displayed with the similar and different features highlighted.

Abstract: We present a method to detect dots in microscope images of tissue samples for the purpose of diagnosis or therapy selection. Dots in tissue arise trough CISH or FISH staining, but also through staining of small cellular compartments, or in other ways. The method is applicable to both brightfield and fluorescence modalities, as well as mass spectrometry imaging methodologies. The method is based on the use of first and second derivatives of the image along the image axes, computed using regularized derivative operators, i.e. Gaussian derivatives. The outputs of these operators are examined at appropriate distances from each location in the image. The found values must have specific signs. If the signs are all correct, these values are multiplied together to obtain a confidence measure for a dot being present at that location. If the signs do not match, no dot is present, and a zero is output.

Abstract: In accordance with the embodiments herein, a method for displaying differences and similarities between tissue samples utilizing a reference database consisting of tissue images, image analysis features, and derived score from patient tissue samples assayed with a tissue-based test for the purpose of scoring said patient sample and guiding treatment based on said score. The method described herein utilizes digital image analysis of a tissue image of one or more tissue sections to extract features which generates a dataset mathematically representing the image. This dataset is then compared to the reference database to determine reference images with similar and different feature values. Those images are then displayed with the similar and different features highlighted.

Abstract: The human vision is limited in terms of perception of color hues and intensities. Moreover, the individual's ability in this context varies greatly from person to person. Herein are described methods to quantify staining of tissue samples via digital tissue image analysis, when staining of a certain biomarker is below or at the threshold of human visual perception, in terms of saturation. This enables for consistent detection of these staining characteristics, which allows for more reproducible data generation through minimizing inter- and intra-observer variability.

Abstract: Staining of tissue is a common approach utilized to visualize a gene product in tissue context. In certain applications, it is necessary to report a sum of events within the tissue as a specific function of the target tissue area, which is a sub-area of the total tissue, as a normalization factor for reporting the quantification. Here, we describe methods of determining target tissue area and reporting a quantification which is ratiometric to the target tissue area, utilizing computer algorithms. It is important to assign a value for the “target tissue area” in scenarios where a tissue area normalization factor is needed in the most pathologically relevant fashion during the application of tissue image analysis. We have created methods for determining and reporting “target tissue area” as normalization factor which are useful in diagnostic applications utilizing image analysis.

Abstract: The present invention concerns detection of specific tissue objects within thin sections of tissue samples as imaged in a brightfield microscope, such as a predetermined type of immune cells, without using a chromogenic stain that is specific to those tissue objects. The invention uses fluorescent stain and fluorescence imaging to detect these tissue objects. By combining a brightfield and a fluorescence image of the same tissue sample, it is possible to automatically identify objects in the brightfield image that have been stained for in the fluorescence image. The fluorescence stain does not affect the appearance of the tissue sample under the brightfield microscope. Therefore, the invention is ideal to automate the collection of training data for machine learning systems that are to be trained to detect these specific tissue objects in brightfield images of tissue that has not been stained to specifically highlight these tissue objects.

Abstract: The disclosure concerns a method for measuring and reporting vascularity in a biological tissue sample. The method generally includes: within a digital image of a tissue section, (i) identifying endothelial cells, lymphatic cells, or a combination thereof; (ii) mapping one or more proximity regions, each of the proximity regions defining an area between detected vessels and a first distance outwardly therefrom; and (iii) calculating one or more of: a vessel proximity score or a hypoxia score, wherein the vessel proximity score relates a composition of objects within the proximity regions, and wherein the hypoxia score relates a composition of tissue within or outside of the proximity regions, respectively.

Abstract: The disclosure concerns a method for extracting spatial distribution statistics from patient tissue samples assayed with a tissue-based test for the purpose of scoring the patient tissue samples and guiding treatment based on the score(s). The method described herein utilizes digital image analysis of an image of one or more tissue sections to extract object-based (e.g., cells) features. The object-based features within the image of the tissue section is further processed using one or more algorithm processes to extract sophisticated spatial distribution features of one or more object type or sub-type in the tissue. Statistics describing the spatial distribution features are summarized to generate a patient-specific diagnostic score, and this score can be evaluated to guide patient treatment decisions.

Abstract: In accordance with the embodiment described herein, we describe a method for evaluating muscle fiber nuclei and non-muscle fiber mononuclear cells, and biomarkers expressed within these and muscle fibers, within the context of muscle tissue using digital tissue image analysis. An algorithm process is applied to histologically stained tissue sections to extract the morphometric, staining, and localization features of a plurality of tissue objects. These features can be further analyzed to describe relationships between tissue objects or tissue object image analysis features. One or more of these image analysis features or relationships between objects and features are summarized to derive a patient-specific score. Patient stratification criteria are applied to the patient-specific score and patient strata membership is evaluated to infer presence of disease, natural course of disease, disease severity, treatment efficacy, or response to a therapy and eligibility for said therapy.

Abstract: The disclosure concerns a method for assessing muscular dystrophy-linked protein expression in muscle fibers using digital image analysis of tissue. The method relates to assessing disease severity in individuals with muscular dystrophy. Muscle tissue samples are obtained from patients submitted for evaluation and processed to produce tissue sections mounted on glass slides which have been stained for a muscular dystrophy-linked protein. Digital images of the stained tissue sections are generated and analyzed by applying an algorithm process implemented by a computer to the images. The algorithm process extracts the morphometric and staining features of the muscular dystrophy-linked protein staining in the tissue, and parameters relating to these features are used to score the disease status for each patient submitted for evaluation.

Abstract: The disclosure concerns a method for extracting geographic distribution statistics from patient tissue samples assayed with a tissue-based test for the purpose of scoring the patient tissue samples and guiding treatment based on the score(s). The method described herein utilizes digital image analysis of an image of one or more tissue sections to extract object-based (e.g., cells) features to generate a data array representing said tissue numerically in image analysis feature space. The numerical representation of the image of the tissue section in image analysis feature space is further processed using one or more algorithm processes to extract sophisticated geographical distribution features of one or more object type or sub-type in the tissue. Statistics describing the geographic distribution features are summarized to generate a patient-specific diagnostic score, and this score can be evaluated to guide patient treatment decisions.

Abstract: The disclosure concerns a method for patient stratification and selection of patients who are candidates for a specific therapy is described which is based on quantifying one or more digital image analysis feature distributions from stained tissue. The method extends beyond the abilities of a manual observer and a microscope, and generally comprises: acquiring digital images of stained tissue sections from patients submitted for evaluation, applying an algorithm process to said images with a computer to extract the morphometric and staining features of image pixels and tissue objects, deriving one or more distribution function for one or more image analysis features, calculating a summary statistic of the one or more distribution functions, and using said summary statistic along with an associated predefined patient stratification paradigm to separate a patient cohort into distinct strata which correspond to a decision to include or exclude a patient for a specific therapy.

Abstract: The disclosure concerns a method for measuring and reporting vascularity in a biological tissue sample. The method generally includes: within a digital image of a tissue section, (i) identifying endothelial cells, lymphatic cells, or a combination thereof; (ii) mapping one or more proximity regions, each of the proximity regions defining an area between detected vessels and a first distance outwardly therefrom; and (iii) calculating one or more of: a vessel proximity score or a hypoxia score, wherein the vessel proximity score relates a composition of objects within the proximity regions, and wherein the hypoxia score relates a composition of tissue within or outside of the proximity regions, respectively.