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

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.

What is claimed is: 
     
         1 . A method comprising:
 obtaining at least one digital image of a stained tissue section;   extracting data associated with at least one staining feature and at least one morphometric feature;   calculating a distribution function which captures the distribution of data for at least one of the staining and morphometric features;   deriving a summary score for a patient from the distribution function;   evaluating the summary score relative to at least one reference value and   selecting the patient as a candidate for a specified therapy based on the summary score.   
     
     
         2 . The method of  claim 1 , wherein the tissue is stained by a method selected from the group consisting of immunohistochemistry, histological dyes, immunofluorescence, and in situ hybridization. 
     
     
         3 . The method of  claim 1 , wherein the at least one morphometric feature is of at least one tissue object and are selected from the group consisting of size, shape, area, texture, organization, and organizational relationship, wherein the at least one tissue object is selected from the group consisting of cells, cell sub-compartments, cell neighborhood, and tissue compartment. 
     
     
         4 . The method of  claim 1 , wherein the at least one staining feature is selected from the group consisting of stain appearance, stain intensity, stain completeness, stain shape, stain texture, and stain area. 
     
     
         5 . The method of  claim 1 , wherein the distribution function is selected from the group consisting of a histogram distribution, a probability distribution function, a cumulative distribution function, and an inverted cumulative distribution function. 
     
     
         6 . The method of  claim 5 , wherein the summary score calculated from the histogram distribution or probability distribution function is selected from the group consisting of minimum, maximum, mean, median, mode, skewness, kurtosis, full-width at half maximum, number of resolvable peaks, area under the curve, and normalness value. 
     
     
         7 . The method of  claim 5 , wherein the summary score calculated from the cumulative density function is selected from the group consisting of an area under the curve (AUC), slope of the curve, slope over a defined range of the curve, difference in image analysis parameter values between two defined cumulative distribution values, difference in cumulative distribution values between two image analysis parameter values, point of maximum deviation from a reference curve, and sum of residuals or squared residuals from a reference curve. 
     
     
         8 . The method of  claim 5 , wherein the summary score calculated from the histogram, probability density, and cumulative distributions can be derived from the group consisting of a measured dynamic range of image analysis feature values, possible dynamic range of an image analysis feature, and a sub-range of image analysis feature values. 
     
     
         9 . The method of  claim 5 , wherein the summary score calculated from the inverted cumulative density function includes one or more Kaplan-Meier statistics values. 
     
     
         10 . The method of  claim 1 , wherein the summary score is derived from the group consisting of a single distribution, multiple distributions describing a single biomarker, or multiple distributions describing multiple biomarkers. 
     
     
         11 . The method of  claim 1 , further comprising applying at least one patient stratification criterium to the summary score to then determine the candidacy of the patient for the specified therapy. 
     
     
         12 . The method of  claim 11 , wherein the patient is determined to be a member of a specific stratum based on the at least one patient stratification criterium. 
     
     
         13 . The method of  claim 11 , wherein the at least one patient stratification criterium defines at least two patient strata based. 
     
     
         14 . The method of  claim 13 , wherein at least one patient stratum is linked to positive response to the specified therapy.