A probabilistic approach to segmentation and classification of neoplasia in uterine cervix images using color and geometric features

Yeshwanth Srinivasan, Dana Hernes, Bhakti Tulpule, Shuyu Yang, Jiangling Guo, Sunanda Mitra, Sriraja Yagneswaran, Brian Nutter, Jose Jeronimo, Benny Phillips, Rodney Long, Daron Ferris

Research output: Contribution to journalConference article

24 Citations (Scopus)

Abstract

Automated segmentation and classification of diagnostic markers in medical imagery are challenging tasks. Numerous algorithms for segmentation and classification based on statistical approaches of varying complexity are found in the literature. However, the design of an efficient and automated algorithm for precise classification of desired diagnostic markers is extremely image-specific. The National Library of Medicine (NLM), in collaboration with the National Cancer Institute (NCI), is creating an archive of 60,000 digitized color images of the uterine cervix. NLM is developing tools for the analysis and dissemination of these images over the Web for the study of visual features correlated with precancerous neoplasia and cancer. To enable indexing of images of the cervix, it is essential to develop algorithms for the segmentation of regions of interest, such as acetowhitened regions, and automatic identification and classification of regions exhibiting mosaicism and punctation. Success of such algorithms depends, primarily, on the selection of relevant features representing the region of interest. We present color and geometric features based statistical classification and segmentation algorithms yielding excellent identification of the regions of interest. The distinct classification of the mosaic regions from the non-mosaic ones has been obtained by clustering multiple geometric and color features of the segmented sections using various morphological and statistical approaches. Such automated classification methodologies will facilitate content-based image retrieval from the digital archive of uterine cervix and have the potential of developing an image based screening tool for cervical cancer.

Original languageEnglish (US)
Article number108
Pages (from-to)995-1003
Number of pages9
JournalProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume5747
Issue numberII
DOIs
StatePublished - Aug 25 2005
EventMedical Imaging 2005 - Image Processing - San Diego, CA, United States
Duration: Feb 13 2005Feb 17 2005

Fingerprint

Cervix Uteri
Color
color
Neoplasms
National Library of Medicine (U.S.)
cancer
medicine
markers
Medicine
Mosaicism
National Cancer Institute (U.S.)
Imagery (Psychotherapy)
Image retrieval
Uterine Cervical Neoplasms
imagery
retrieval
Cluster Analysis
Screening
screening
methodology

Keywords

  • Automatic segmentation
  • Cervical cancer
  • Image morphology
  • Uterine cervix

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Biomaterials
  • Atomic and Molecular Physics, and Optics
  • Radiology Nuclear Medicine and imaging

Cite this

A probabilistic approach to segmentation and classification of neoplasia in uterine cervix images using color and geometric features. / Srinivasan, Yeshwanth; Hernes, Dana; Tulpule, Bhakti; Yang, Shuyu; Guo, Jiangling; Mitra, Sunanda; Yagneswaran, Sriraja; Nutter, Brian; Jeronimo, Jose; Phillips, Benny; Long, Rodney; Ferris, Daron.

In: Progress in Biomedical Optics and Imaging - Proceedings of SPIE, Vol. 5747, No. II, 108, 25.08.2005, p. 995-1003.

Research output: Contribution to journalConference article

Srinivasan, Y, Hernes, D, Tulpule, B, Yang, S, Guo, J, Mitra, S, Yagneswaran, S, Nutter, B, Jeronimo, J, Phillips, B, Long, R & Ferris, D 2005, 'A probabilistic approach to segmentation and classification of neoplasia in uterine cervix images using color and geometric features', Progress in Biomedical Optics and Imaging - Proceedings of SPIE, vol. 5747, no. II, 108, pp. 995-1003. https://doi.org/10.1117/12.597075
Srinivasan, Yeshwanth ; Hernes, Dana ; Tulpule, Bhakti ; Yang, Shuyu ; Guo, Jiangling ; Mitra, Sunanda ; Yagneswaran, Sriraja ; Nutter, Brian ; Jeronimo, Jose ; Phillips, Benny ; Long, Rodney ; Ferris, Daron. / A probabilistic approach to segmentation and classification of neoplasia in uterine cervix images using color and geometric features. In: Progress in Biomedical Optics and Imaging - Proceedings of SPIE. 2005 ; Vol. 5747, No. II. pp. 995-1003.
@article{48ff8472d32849a3aa0df8e7ef6dfd33,
title = "A probabilistic approach to segmentation and classification of neoplasia in uterine cervix images using color and geometric features",
abstract = "Automated segmentation and classification of diagnostic markers in medical imagery are challenging tasks. Numerous algorithms for segmentation and classification based on statistical approaches of varying complexity are found in the literature. However, the design of an efficient and automated algorithm for precise classification of desired diagnostic markers is extremely image-specific. The National Library of Medicine (NLM), in collaboration with the National Cancer Institute (NCI), is creating an archive of 60,000 digitized color images of the uterine cervix. NLM is developing tools for the analysis and dissemination of these images over the Web for the study of visual features correlated with precancerous neoplasia and cancer. To enable indexing of images of the cervix, it is essential to develop algorithms for the segmentation of regions of interest, such as acetowhitened regions, and automatic identification and classification of regions exhibiting mosaicism and punctation. Success of such algorithms depends, primarily, on the selection of relevant features representing the region of interest. We present color and geometric features based statistical classification and segmentation algorithms yielding excellent identification of the regions of interest. The distinct classification of the mosaic regions from the non-mosaic ones has been obtained by clustering multiple geometric and color features of the segmented sections using various morphological and statistical approaches. Such automated classification methodologies will facilitate content-based image retrieval from the digital archive of uterine cervix and have the potential of developing an image based screening tool for cervical cancer.",
keywords = "Automatic segmentation, Cervical cancer, Image morphology, Uterine cervix",
author = "Yeshwanth Srinivasan and Dana Hernes and Bhakti Tulpule and Shuyu Yang and Jiangling Guo and Sunanda Mitra and Sriraja Yagneswaran and Brian Nutter and Jose Jeronimo and Benny Phillips and Rodney Long and Daron Ferris",
year = "2005",
month = "8",
day = "25",
doi = "10.1117/12.597075",
language = "English (US)",
volume = "5747",
pages = "995--1003",
journal = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",
issn = "1605-7422",
publisher = "SPIE",
number = "II",

}

TY - JOUR

T1 - A probabilistic approach to segmentation and classification of neoplasia in uterine cervix images using color and geometric features

AU - Srinivasan, Yeshwanth

AU - Hernes, Dana

AU - Tulpule, Bhakti

AU - Yang, Shuyu

AU - Guo, Jiangling

AU - Mitra, Sunanda

AU - Yagneswaran, Sriraja

AU - Nutter, Brian

AU - Jeronimo, Jose

AU - Phillips, Benny

AU - Long, Rodney

AU - Ferris, Daron

PY - 2005/8/25

Y1 - 2005/8/25

N2 - Automated segmentation and classification of diagnostic markers in medical imagery are challenging tasks. Numerous algorithms for segmentation and classification based on statistical approaches of varying complexity are found in the literature. However, the design of an efficient and automated algorithm for precise classification of desired diagnostic markers is extremely image-specific. The National Library of Medicine (NLM), in collaboration with the National Cancer Institute (NCI), is creating an archive of 60,000 digitized color images of the uterine cervix. NLM is developing tools for the analysis and dissemination of these images over the Web for the study of visual features correlated with precancerous neoplasia and cancer. To enable indexing of images of the cervix, it is essential to develop algorithms for the segmentation of regions of interest, such as acetowhitened regions, and automatic identification and classification of regions exhibiting mosaicism and punctation. Success of such algorithms depends, primarily, on the selection of relevant features representing the region of interest. We present color and geometric features based statistical classification and segmentation algorithms yielding excellent identification of the regions of interest. The distinct classification of the mosaic regions from the non-mosaic ones has been obtained by clustering multiple geometric and color features of the segmented sections using various morphological and statistical approaches. Such automated classification methodologies will facilitate content-based image retrieval from the digital archive of uterine cervix and have the potential of developing an image based screening tool for cervical cancer.

AB - Automated segmentation and classification of diagnostic markers in medical imagery are challenging tasks. Numerous algorithms for segmentation and classification based on statistical approaches of varying complexity are found in the literature. However, the design of an efficient and automated algorithm for precise classification of desired diagnostic markers is extremely image-specific. The National Library of Medicine (NLM), in collaboration with the National Cancer Institute (NCI), is creating an archive of 60,000 digitized color images of the uterine cervix. NLM is developing tools for the analysis and dissemination of these images over the Web for the study of visual features correlated with precancerous neoplasia and cancer. To enable indexing of images of the cervix, it is essential to develop algorithms for the segmentation of regions of interest, such as acetowhitened regions, and automatic identification and classification of regions exhibiting mosaicism and punctation. Success of such algorithms depends, primarily, on the selection of relevant features representing the region of interest. We present color and geometric features based statistical classification and segmentation algorithms yielding excellent identification of the regions of interest. The distinct classification of the mosaic regions from the non-mosaic ones has been obtained by clustering multiple geometric and color features of the segmented sections using various morphological and statistical approaches. Such automated classification methodologies will facilitate content-based image retrieval from the digital archive of uterine cervix and have the potential of developing an image based screening tool for cervical cancer.

KW - Automatic segmentation

KW - Cervical cancer

KW - Image morphology

KW - Uterine cervix

UR - http://www.scopus.com/inward/record.url?scp=23844445227&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=23844445227&partnerID=8YFLogxK

U2 - 10.1117/12.597075

DO - 10.1117/12.597075

M3 - Conference article

AN - SCOPUS:23844445227

VL - 5747

SP - 995

EP - 1003

JO - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

JF - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

SN - 1605-7422

IS - II

M1 - 108

ER -