Histological image processing features induce a quantitative characterization of chronic tumor hypoxia

Andrew Sundstrom, Elda Grabocka, Dafna Bar-Sagi, Bhubaneswar Mishra

Research output: Contribution to journalArticle

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.

Original languageEnglish (US)
Article numbere0153623
JournalPLoS One
Volume11
Issue number4
DOIs
StatePublished - Apr 1 2016

Fingerprint

Tumors
hypoxia
Image processing
image analysis
neoplasms
Histology
histology
Blood Vessels
Colorectal Neoplasms
Linear Models
Neoplasms
Staining and Labeling
Blood vessels
blood vessels
Linear regression
space and time
Tumor Hypoxia
Tissue
Sampling
therapeutics

ASJC Scopus subject areas

  • Agricultural and Biological Sciences(all)
  • Biochemistry, Genetics and Molecular Biology(all)
  • Medicine(all)

Cite this

Histological image processing features induce a quantitative characterization of chronic tumor hypoxia. / Sundstrom, Andrew; Grabocka, Elda; Bar-Sagi, Dafna; Mishra, Bhubaneswar.

In: PLoS One, Vol. 11, No. 4, e0153623, 01.04.2016.

Research output: Contribution to journalArticle

@article{b635e4f888144e608b0415ac9308a0bb,
title = "Histological image processing features induce a quantitative characterization of chronic tumor hypoxia",
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.",
author = "Andrew Sundstrom and Elda Grabocka and Dafna Bar-Sagi and Bhubaneswar Mishra",
year = "2016",
month = "4",
day = "1",
doi = "10.1371/journal.pone.0153623",
language = "English (US)",
volume = "11",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "4",

}

TY - JOUR

T1 - Histological image processing features induce a quantitative characterization of chronic tumor hypoxia

AU - Sundstrom, Andrew

AU - Grabocka, Elda

AU - Bar-Sagi, Dafna

AU - Mishra, Bhubaneswar

PY - 2016/4/1

Y1 - 2016/4/1

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=84966376758&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84966376758&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0153623

DO - 10.1371/journal.pone.0153623

M3 - Article

VL - 11

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 4

M1 - e0153623

ER -