Histological Image Processing Features Induce a Quantitative Characterization of Chronic Tumor Hypoxia.
Bottom Line:
We use image-processing algorithms to develop a set of candidate image features that can formulate just such a quantitative description of xenographed colorectal chronic tumor hypoxia.Two features in particular give low-variance measures of chronic hypoxia near a vessel: intensity sampling that extends radially away from approximated blood vessel centroids, and multithresholding to segment tumor tissue into normal, hypoxic, and necrotic regions.From these features we derive a spatiotemporal logical expression whose truth value depends on its predicate clauses that are grounded in this histological evidence.
View Article:
PubMed Central - PubMed
Affiliation: Department of Pharmacology and Systems Therapeutics, Icahn School of Medicine at Mount Sinai, New York, NY, United States of America.
ABSTRACT
Hypoxia in tumors signifies resistance to therapy. Despite a wealth of tumor histology data, including anti-pimonidazole staining, no current methods use these data to induce a quantitative characterization of chronic tumor hypoxia in time and space. We use image-processing algorithms to develop a set of candidate image features that can formulate just such a quantitative description of xenographed colorectal chronic tumor hypoxia. Two features in particular give low-variance measures of chronic hypoxia near a vessel: intensity sampling that extends radially away from approximated blood vessel centroids, and multithresholding to segment tumor tissue into normal, hypoxic, and necrotic regions. From these features we derive a spatiotemporal logical expression whose truth value depends on its predicate clauses that are grounded in this histological evidence. As an alternative to the spatiotemporal logical formulation, we also propose a way to formulate a linear regression function that uses all of the image features to learn what chronic hypoxia looks like, and then gives a quantitative similarity score once it is trained on a set of histology images. No MeSH data available. Related in: MedlinePlus |
Related In:
Results -
Collection
License getmorefigures.php?uid=PMC4836667&req=5
Mentions: Suppose we are in a 2D universe. From axiom A1 above, we can immediately write our first proposition term. If we hold x2 fixed at any arbitrary value and test along x1 from an arbitrary min1 to an arbitrary max1 value, x1(min1)→x1(max1), then we expect to encounter tissue types in the following pattern: {V, N}→H → {V, N}→H → …., that is, any contiguous V or N region is separated by a contiguous H region (see trajectory (A) in Fig 7). This is equivalent to axiom A1, which states that V and N are invalid neighbors, their regions cannot abut. Suppose we have a primitive state variable function T: (x1, x2)→{H, V, N} that given a coordinate (x1, x2) returns the tissue type at that coordinate, namely H, V, or N. In terms of our spatiotemporal logic, we can implement a verification of axiom A1 with the following proposition term:¬ [(T(x1,x2)=N)Ux1,max1-min1(T(x1,x2)=V)]∧¬ [(T(x1,x2)=V)Ux1,max1-min1(T(x1,x2)=N)].(1) |
View Article: PubMed Central - PubMed
Affiliation: Department of Pharmacology and Systems Therapeutics, Icahn School of Medicine at Mount Sinai, New York, NY, United States of America.
No MeSH data available.