Flagship Biosciences, Inc.

Osi Pharmaceuticals, Inc.

Joseph Krueger

Holger Lange

Nathan T Martin

George David Young

Joshua C Black

Famke Aeffner

Anthony John Milici

Trevor Johnson

Frank Voelker

Mirza Peljto

Steven J Potts

Julie Kan

Salam A Shaaban

Cris L Luengo Hendriks

Logan Jerome Cerkovnik

G David Young

Maryland Franklin

Allison S Harney

Robert C Wild

Chris L Luengo Hendriks

Carsten Schnatwinkel

Kristin Wilson

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.

Method for digitally generating scores for multiple diagnostic tests from tissue assayed with a single test

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.

Method for comparative visualization of image analysis features of tissue

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.

Method for detecting immunostaining below the threshold of visual perception

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.

Method for assigning tissue normalization factors for digital image analysis

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.

Method for scoring pathology images using spatial statistics of cells in tissues

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.

Method for stratifying and selecting candidates for receiving a specific therapeutic approach

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. The score of disease status is ultimately used to infer disease severity, monitor the efficacy of a therapeutic approach, or select patients as candidates for a therapeutic approach.

Methods for quantitative assessment of muscle fibers in muscular dystrophy

Methods for cell-based tissue analysis utilize modern trends in digital microscopy to obtain, process, calibrate, and analyze digital images of tissue sections to quantify cell-based data for improved histological analysis. Using data from multiple images of a common tissue section, or data from images of multiple tissue sections, additional degrees of freedom are realized and the resulting analysis provides added depth to histological analysis of tissue samples. With computerized analytical methods, speed and accuracy of histological analysis is greatly improved.

Cell-based tissue analysis

Systems and methods relating to a cell-based pattern recognition tool for microscopy images from tissue sections are described, wherein cell features are extracted and a classifier is built in accordance with a particular application using an interactive training tied to a computerized platform, the result is an application-specific classifier that further processes images in accordance with the specific application, thereby tuning an automated process for cell based pattern recognition.

Computerized methods for cell-based pattern recognition

This disclosure concerns methods for evaluating inflammatory cells and modulators of the inflammatory response in tumor tissue and other relevant tissue types. The methods entail: obtaining a tissue sample and processing said tissue sample to produce histologic slides of tissue sections; staining of the tissue sections to identify inflammatory cells and modulators of the inflammatory response; digitizing slides to produce an image of the stained tissue sections; digitally stratifying the tissue sample into tumor and other relevant tissue compartments; and using digital image analysis to quantify cell-based and cell population-based features. The quantification of cell-based and cell population-based features within a tissue compartment of interest is used to develop a summary score of the immune system-tissue compartment of interest interaction. Patient stratification and selection as candidates for a therapeutic approach is ultimately based on the summary score value.

Digital image analysis of inflammatory cells and mediators of inflammation

The present invention provides tumor cell preparations for use as models of the EMT process for use in the identification of anti-cancer agents, wherein said tumor cell preparations comprise cells of the epithelial tumor cell line CFPAC-1, which are stimulated by receptor ligands to induce EMT, or which have been engineered to inducibly express a protein that stimulates EMT. The present invention also provides methods of identifying potential anti-cancer agents by using such tumor cell preparations to identify agents that inhibit EMT, stimulate MET, or inhibit the growth of mesenchymal-like cells. Such agents should be particularly useful when used in conjunction with other anti-cancer drugs such as EGFR and IGF-1R kinase inhibitors, which appear to be less effective at inhibiting tumor cells that have undergone an EMT.

Growing community of inventors

Andover, MA, United States of America

Joseph Krueger