Network cycle features: Application to computer-aided Gleason grading of prostate cancer histopathological images

Parmeshwar Khurd, Leo Grady, Ali Kamen, Summer Gibbs, Elizabeth M. Genega, John V. Frangioni

Research output: Chapter in Book/Report/Conference proceedingConference contribution

27 Citations (Scopus)

Abstract

Features extracted from cell networks have become popular tools in histological image analysis. However, existing features do not take sufficient advantage of the cycle structure present within the cell networks. We introduce a new class of network cycle features that take advantage of such structures. We demonstrate the utility of these features for automated prostate cancer scoring using histological images. Prostate cancer is commonly scored by pathologists using the Gleason grading system and our automated system based upon network cycle features serves an important need in making this process less labor-intensive and more reproducible. Our system first extracts the cells from the histological images, computes networks from the cell locations and then computes features based upon statistics for the different cycles present in these networks. Using an SVM (Support Vector Machine) classifier on these features, we demonstrate the efficacy of our system in distinguishing between grade 3 and grade 4 prostate tumors. We also show the superiority of our approach over previously developed systems for this problem based upon texture features, fractal features and alternative network features.

Original languageEnglish (US)
Title of host publication2011 8th IEEE International Symposium on Biomedical Imaging
Subtitle of host publicationFrom Nano to Macro, ISBI'11
Pages1632-1636
Number of pages5
DOIs
StatePublished - 2011
Externally publishedYes
Event2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11 - Chicago, IL, United States
Duration: Mar 30 2011Apr 2 2011

Other

Other2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11
CountryUnited States
CityChicago, IL
Period3/30/114/2/11

Fingerprint

Neoplasm Grading
Fractals
Image analysis
Support vector machines
Tumors
Prostatic Neoplasms
Classifiers
Textures
Statistics
Personnel
Cell Extracts
Prostate
Neoplasms

Keywords

  • classification
  • Gleason grading
  • network features
  • prostate cancer

ASJC Scopus subject areas

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging

Cite this

Khurd, P., Grady, L., Kamen, A., Gibbs, S., Genega, E. M., & Frangioni, J. V. (2011). Network cycle features: Application to computer-aided Gleason grading of prostate cancer histopathological images. In 2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11 (pp. 1632-1636). [5872716] https://doi.org/10.1109/ISBI.2011.5872716

Network cycle features : Application to computer-aided Gleason grading of prostate cancer histopathological images. / Khurd, Parmeshwar; Grady, Leo; Kamen, Ali; Gibbs, Summer; Genega, Elizabeth M.; Frangioni, John V.

2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11. 2011. p. 1632-1636 5872716.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Khurd, P, Grady, L, Kamen, A, Gibbs, S, Genega, EM & Frangioni, JV 2011, Network cycle features: Application to computer-aided Gleason grading of prostate cancer histopathological images. in 2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11., 5872716, pp. 1632-1636, 2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11, Chicago, IL, United States, 3/30/11. https://doi.org/10.1109/ISBI.2011.5872716
Khurd P, Grady L, Kamen A, Gibbs S, Genega EM, Frangioni JV. Network cycle features: Application to computer-aided Gleason grading of prostate cancer histopathological images. In 2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11. 2011. p. 1632-1636. 5872716 https://doi.org/10.1109/ISBI.2011.5872716
Khurd, Parmeshwar ; Grady, Leo ; Kamen, Ali ; Gibbs, Summer ; Genega, Elizabeth M. ; Frangioni, John V. / Network cycle features : Application to computer-aided Gleason grading of prostate cancer histopathological images. 2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11. 2011. pp. 1632-1636
@inproceedings{73b12e6b9f0d477699d36dd3798fa411,
title = "Network cycle features: Application to computer-aided Gleason grading of prostate cancer histopathological images",
abstract = "Features extracted from cell networks have become popular tools in histological image analysis. However, existing features do not take sufficient advantage of the cycle structure present within the cell networks. We introduce a new class of network cycle features that take advantage of such structures. We demonstrate the utility of these features for automated prostate cancer scoring using histological images. Prostate cancer is commonly scored by pathologists using the Gleason grading system and our automated system based upon network cycle features serves an important need in making this process less labor-intensive and more reproducible. Our system first extracts the cells from the histological images, computes networks from the cell locations and then computes features based upon statistics for the different cycles present in these networks. Using an SVM (Support Vector Machine) classifier on these features, we demonstrate the efficacy of our system in distinguishing between grade 3 and grade 4 prostate tumors. We also show the superiority of our approach over previously developed systems for this problem based upon texture features, fractal features and alternative network features.",
keywords = "classification, Gleason grading, network features, prostate cancer",
author = "Parmeshwar Khurd and Leo Grady and Ali Kamen and Summer Gibbs and Genega, {Elizabeth M.} and Frangioni, {John V.}",
year = "2011",
doi = "10.1109/ISBI.2011.5872716",
language = "English (US)",
isbn = "9781424441280",
pages = "1632--1636",
booktitle = "2011 8th IEEE International Symposium on Biomedical Imaging",

}

TY - GEN

T1 - Network cycle features

T2 - Application to computer-aided Gleason grading of prostate cancer histopathological images

AU - Khurd, Parmeshwar

AU - Grady, Leo

AU - Kamen, Ali

AU - Gibbs, Summer

AU - Genega, Elizabeth M.

AU - Frangioni, John V.

PY - 2011

Y1 - 2011

N2 - Features extracted from cell networks have become popular tools in histological image analysis. However, existing features do not take sufficient advantage of the cycle structure present within the cell networks. We introduce a new class of network cycle features that take advantage of such structures. We demonstrate the utility of these features for automated prostate cancer scoring using histological images. Prostate cancer is commonly scored by pathologists using the Gleason grading system and our automated system based upon network cycle features serves an important need in making this process less labor-intensive and more reproducible. Our system first extracts the cells from the histological images, computes networks from the cell locations and then computes features based upon statistics for the different cycles present in these networks. Using an SVM (Support Vector Machine) classifier on these features, we demonstrate the efficacy of our system in distinguishing between grade 3 and grade 4 prostate tumors. We also show the superiority of our approach over previously developed systems for this problem based upon texture features, fractal features and alternative network features.

AB - Features extracted from cell networks have become popular tools in histological image analysis. However, existing features do not take sufficient advantage of the cycle structure present within the cell networks. We introduce a new class of network cycle features that take advantage of such structures. We demonstrate the utility of these features for automated prostate cancer scoring using histological images. Prostate cancer is commonly scored by pathologists using the Gleason grading system and our automated system based upon network cycle features serves an important need in making this process less labor-intensive and more reproducible. Our system first extracts the cells from the histological images, computes networks from the cell locations and then computes features based upon statistics for the different cycles present in these networks. Using an SVM (Support Vector Machine) classifier on these features, we demonstrate the efficacy of our system in distinguishing between grade 3 and grade 4 prostate tumors. We also show the superiority of our approach over previously developed systems for this problem based upon texture features, fractal features and alternative network features.

KW - classification

KW - Gleason grading

KW - network features

KW - prostate cancer

UR - http://www.scopus.com/inward/record.url?scp=80055055231&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80055055231&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2011.5872716

DO - 10.1109/ISBI.2011.5872716

M3 - Conference contribution

AN - SCOPUS:80055055231

SN - 9781424441280

SP - 1632

EP - 1636

BT - 2011 8th IEEE International Symposium on Biomedical Imaging

ER -