Automated image analysis of uterine cervical images

Wenjing Li, Jia Gu, Daron Gale Ferris, Allen Poirson

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

16 Citations (Scopus)

Abstract

Cervical Cancer is the second most common cancer among women worldwide and the leading cause of cancer mortality of women in developing countries. If detected early and treated adequately, cervical cancer can be virtually prevented. Cervical precursor lesions and invasive cancer exhibit certain morphologic features that can be identified during a visual inspection exam. Digital imaging technologies allow us to assist the physician with a Computer-Aided Diagnosis (CAD) system. In colposcopy, epithelium that turns white after application of acetic acid is called acetowhite epithelium. Acetowhite epithelium is one of the major diagnostic features observed in detecting cancer and pre-cancerous regions. Automatic extraction of acetowhite regions from cervical images has been a challenging task due to specular reflection, various illumination conditions, and most importantly, large intra-patient variation. This paper presents a multi-step acetowhite region detection system to analyze the acetowhite lesions in cervical images automatically. First, the system calibrates the color of the cervical images to be independent of screening devices. Second, the anatomy of the uterine cervix is analyzed in terms of cervix region, external os region, columnar region, and squamous region. Third, the squamous region is further analyzed and subregions based on three levels of acetowhite are identified. The extracted acetowhite regions are accompanied by color scores to indicate the different levels of acetowhite. The system has been evaluated by 40 human subjects' data and demonstrates high correlation with experts' annotations.

Original languageEnglish (US)
Title of host publicationMedical Imaging 2007
Subtitle of host publicationComputer-Aided Diagnosis
Volume6514
EditionPART 2
DOIs
StatePublished - Oct 18 2007
EventMedical Imaging 2007: Computer-Aided Diagnosis - San Diego, CA, United States
Duration: Feb 20 2007Feb 22 2007

Other

OtherMedical Imaging 2007: Computer-Aided Diagnosis
CountryUnited States
CitySan Diego, CA
Period2/20/072/22/07

Fingerprint

Image analysis
Color
Developing countries
Acetic acid
Screening
Lighting
Inspection
Imaging techniques

Keywords

  • Acetowhite
  • Cervical cancer
  • Colposcopy
  • Computer-aided diagnosis (CAD)

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Li, W., Gu, J., Ferris, D. G., & Poirson, A. (2007). Automated image analysis of uterine cervical images. In Medical Imaging 2007: Computer-Aided Diagnosis (PART 2 ed., Vol. 6514). [65142P] https://doi.org/10.1117/12.708710

Automated image analysis of uterine cervical images. / Li, Wenjing; Gu, Jia; Ferris, Daron Gale; Poirson, Allen.

Medical Imaging 2007: Computer-Aided Diagnosis. Vol. 6514 PART 2. ed. 2007. 65142P.

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

Li, W, Gu, J, Ferris, DG & Poirson, A 2007, Automated image analysis of uterine cervical images. in Medical Imaging 2007: Computer-Aided Diagnosis. PART 2 edn, vol. 6514, 65142P, Medical Imaging 2007: Computer-Aided Diagnosis, San Diego, CA, United States, 2/20/07. https://doi.org/10.1117/12.708710
Li W, Gu J, Ferris DG, Poirson A. Automated image analysis of uterine cervical images. In Medical Imaging 2007: Computer-Aided Diagnosis. PART 2 ed. Vol. 6514. 2007. 65142P https://doi.org/10.1117/12.708710
Li, Wenjing ; Gu, Jia ; Ferris, Daron Gale ; Poirson, Allen. / Automated image analysis of uterine cervical images. Medical Imaging 2007: Computer-Aided Diagnosis. Vol. 6514 PART 2. ed. 2007.
@inproceedings{8837d9b5ca5d446a8eadb79ed5d298a1,
title = "Automated image analysis of uterine cervical images",
abstract = "Cervical Cancer is the second most common cancer among women worldwide and the leading cause of cancer mortality of women in developing countries. If detected early and treated adequately, cervical cancer can be virtually prevented. Cervical precursor lesions and invasive cancer exhibit certain morphologic features that can be identified during a visual inspection exam. Digital imaging technologies allow us to assist the physician with a Computer-Aided Diagnosis (CAD) system. In colposcopy, epithelium that turns white after application of acetic acid is called acetowhite epithelium. Acetowhite epithelium is one of the major diagnostic features observed in detecting cancer and pre-cancerous regions. Automatic extraction of acetowhite regions from cervical images has been a challenging task due to specular reflection, various illumination conditions, and most importantly, large intra-patient variation. This paper presents a multi-step acetowhite region detection system to analyze the acetowhite lesions in cervical images automatically. First, the system calibrates the color of the cervical images to be independent of screening devices. Second, the anatomy of the uterine cervix is analyzed in terms of cervix region, external os region, columnar region, and squamous region. Third, the squamous region is further analyzed and subregions based on three levels of acetowhite are identified. The extracted acetowhite regions are accompanied by color scores to indicate the different levels of acetowhite. The system has been evaluated by 40 human subjects' data and demonstrates high correlation with experts' annotations.",
keywords = "Acetowhite, Cervical cancer, Colposcopy, Computer-aided diagnosis (CAD)",
author = "Wenjing Li and Jia Gu and Ferris, {Daron Gale} and Allen Poirson",
year = "2007",
month = "10",
day = "18",
doi = "10.1117/12.708710",
language = "English (US)",
isbn = "0819466328",
volume = "6514",
booktitle = "Medical Imaging 2007",
edition = "PART 2",

}

TY - GEN

T1 - Automated image analysis of uterine cervical images

AU - Li, Wenjing

AU - Gu, Jia

AU - Ferris, Daron Gale

AU - Poirson, Allen

PY - 2007/10/18

Y1 - 2007/10/18

N2 - Cervical Cancer is the second most common cancer among women worldwide and the leading cause of cancer mortality of women in developing countries. If detected early and treated adequately, cervical cancer can be virtually prevented. Cervical precursor lesions and invasive cancer exhibit certain morphologic features that can be identified during a visual inspection exam. Digital imaging technologies allow us to assist the physician with a Computer-Aided Diagnosis (CAD) system. In colposcopy, epithelium that turns white after application of acetic acid is called acetowhite epithelium. Acetowhite epithelium is one of the major diagnostic features observed in detecting cancer and pre-cancerous regions. Automatic extraction of acetowhite regions from cervical images has been a challenging task due to specular reflection, various illumination conditions, and most importantly, large intra-patient variation. This paper presents a multi-step acetowhite region detection system to analyze the acetowhite lesions in cervical images automatically. First, the system calibrates the color of the cervical images to be independent of screening devices. Second, the anatomy of the uterine cervix is analyzed in terms of cervix region, external os region, columnar region, and squamous region. Third, the squamous region is further analyzed and subregions based on three levels of acetowhite are identified. The extracted acetowhite regions are accompanied by color scores to indicate the different levels of acetowhite. The system has been evaluated by 40 human subjects' data and demonstrates high correlation with experts' annotations.

AB - Cervical Cancer is the second most common cancer among women worldwide and the leading cause of cancer mortality of women in developing countries. If detected early and treated adequately, cervical cancer can be virtually prevented. Cervical precursor lesions and invasive cancer exhibit certain morphologic features that can be identified during a visual inspection exam. Digital imaging technologies allow us to assist the physician with a Computer-Aided Diagnosis (CAD) system. In colposcopy, epithelium that turns white after application of acetic acid is called acetowhite epithelium. Acetowhite epithelium is one of the major diagnostic features observed in detecting cancer and pre-cancerous regions. Automatic extraction of acetowhite regions from cervical images has been a challenging task due to specular reflection, various illumination conditions, and most importantly, large intra-patient variation. This paper presents a multi-step acetowhite region detection system to analyze the acetowhite lesions in cervical images automatically. First, the system calibrates the color of the cervical images to be independent of screening devices. Second, the anatomy of the uterine cervix is analyzed in terms of cervix region, external os region, columnar region, and squamous region. Third, the squamous region is further analyzed and subregions based on three levels of acetowhite are identified. The extracted acetowhite regions are accompanied by color scores to indicate the different levels of acetowhite. The system has been evaluated by 40 human subjects' data and demonstrates high correlation with experts' annotations.

KW - Acetowhite

KW - Cervical cancer

KW - Colposcopy

KW - Computer-aided diagnosis (CAD)

UR - http://www.scopus.com/inward/record.url?scp=35248813945&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=35248813945&partnerID=8YFLogxK

U2 - 10.1117/12.708710

DO - 10.1117/12.708710

M3 - Conference contribution

SN - 0819466328

SN - 9780819466327

VL - 6514

BT - Medical Imaging 2007

ER -