Automated segmentation algorithm for detection of changes in vaginal epithelial morphology using optical coherence tomography

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

We have explored the use of optical coherence tomography (OCT) as a noninvasive tool for assessing the toxicity of topical microbicides, products used to prevent HIV, by monitoring the integrity of the vaginal epithelium. A novel feature-based segmentation algorithm using a nearest-neighbor classifier was developed to monitor changes in the morphology of vaginal epithelium. The two-step automated algorithm yielded OCT images with a clearly defined epithelial layer, enabling differentiation of normal and damaged tissue. The algorithm was robust in that it was able to discriminate the epithelial layer from underlying stroma as well as residual microbicide product on the surface. This segmentation technique for OCT images has the potential to be readily adaptable to the clinical setting for noninvasively defining the boundaries of the epithelium, enabling quantifiable assessment of microbicide-induced damage in vaginal tissue.

Original languageEnglish (US)
Article number116004
JournalJournal of Biomedical Optics
Volume17
Issue number11
DOIs
StatePublished - Nov 2012

Fingerprint

epithelium
Optical tomography
tomography
Anti-Infective Agents
Tissue
human immunodeficiency virus
Local Anti-Infective Agents
products
classifiers
toxicity
integrity
Toxicity
Classifiers
damage
Monitoring

Keywords

  • image segmentation
  • oct
  • optical coherence tomography
  • vaginal epithelium

ASJC Scopus subject areas

  • Biomedical Engineering
  • Biomaterials
  • Electronic, Optical and Magnetic Materials
  • Atomic and Molecular Physics, and Optics

Cite this

@article{4b0a5b867c304f0983b94a012392581a,
title = "Automated segmentation algorithm for detection of changes in vaginal epithelial morphology using optical coherence tomography",
abstract = "We have explored the use of optical coherence tomography (OCT) as a noninvasive tool for assessing the toxicity of topical microbicides, products used to prevent HIV, by monitoring the integrity of the vaginal epithelium. A novel feature-based segmentation algorithm using a nearest-neighbor classifier was developed to monitor changes in the morphology of vaginal epithelium. The two-step automated algorithm yielded OCT images with a clearly defined epithelial layer, enabling differentiation of normal and damaged tissue. The algorithm was robust in that it was able to discriminate the epithelial layer from underlying stroma as well as residual microbicide product on the surface. This segmentation technique for OCT images has the potential to be readily adaptable to the clinical setting for noninvasively defining the boundaries of the epithelium, enabling quantifiable assessment of microbicide-induced damage in vaginal tissue.",
keywords = "image segmentation, oct, optical coherence tomography, vaginal epithelium",
author = "Shahab Chitchian and Kathleen Vincent and Gracie Vargas and Massoud Motamedi",
year = "2012",
month = "11",
doi = "10.1117/1.JBO.17.11.116004",
language = "English (US)",
volume = "17",
journal = "Journal of Biomedical Optics",
issn = "1083-3668",
publisher = "SPIE",
number = "11",

}

TY - JOUR

T1 - Automated segmentation algorithm for detection of changes in vaginal epithelial morphology using optical coherence tomography

AU - Chitchian, Shahab

AU - Vincent, Kathleen

AU - Vargas, Gracie

AU - Motamedi, Massoud

PY - 2012/11

Y1 - 2012/11

N2 - We have explored the use of optical coherence tomography (OCT) as a noninvasive tool for assessing the toxicity of topical microbicides, products used to prevent HIV, by monitoring the integrity of the vaginal epithelium. A novel feature-based segmentation algorithm using a nearest-neighbor classifier was developed to monitor changes in the morphology of vaginal epithelium. The two-step automated algorithm yielded OCT images with a clearly defined epithelial layer, enabling differentiation of normal and damaged tissue. The algorithm was robust in that it was able to discriminate the epithelial layer from underlying stroma as well as residual microbicide product on the surface. This segmentation technique for OCT images has the potential to be readily adaptable to the clinical setting for noninvasively defining the boundaries of the epithelium, enabling quantifiable assessment of microbicide-induced damage in vaginal tissue.

AB - We have explored the use of optical coherence tomography (OCT) as a noninvasive tool for assessing the toxicity of topical microbicides, products used to prevent HIV, by monitoring the integrity of the vaginal epithelium. A novel feature-based segmentation algorithm using a nearest-neighbor classifier was developed to monitor changes in the morphology of vaginal epithelium. The two-step automated algorithm yielded OCT images with a clearly defined epithelial layer, enabling differentiation of normal and damaged tissue. The algorithm was robust in that it was able to discriminate the epithelial layer from underlying stroma as well as residual microbicide product on the surface. This segmentation technique for OCT images has the potential to be readily adaptable to the clinical setting for noninvasively defining the boundaries of the epithelium, enabling quantifiable assessment of microbicide-induced damage in vaginal tissue.

KW - image segmentation

KW - oct

KW - optical coherence tomography

KW - vaginal epithelium

UR - http://www.scopus.com/inward/record.url?scp=84870575875&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84870575875&partnerID=8YFLogxK

U2 - 10.1117/1.JBO.17.11.116004

DO - 10.1117/1.JBO.17.11.116004

M3 - Article

VL - 17

JO - Journal of Biomedical Optics

JF - Journal of Biomedical Optics

SN - 1083-3668

IS - 11

M1 - 116004

ER -