Automatic detection of anatomical landmarks in uterine cervix images

Hayit Greenspan; Shiri Gordon; Gali Zimmerman; Shelly Lotenberg; Jose Jeronimo; Sameer Antani; Rodney Long

doi:10.1109/TMI.2008.2007823

Automatic detection of anatomical landmarks in uterine cervix images

Hayit Greenspan^*
, Shiri Gordon
, Gali Zimmerman
, Shelly Lotenberg
, Jose Jeronimo
, Sameer Antani
, Rodney Long

^*Corresponding author for this work

School of Biomedical Engineering

Tel Aviv University
Superfish Ltd.
Mobileye Vision Technologies Ltd.
National Institutes of Health
PATH

Research output: Contribution to journal › Article › peer-review

65 Scopus citations

Abstract

The work focuses on a unique medical repository of digital cervicographic images (Cervigrams) collected by the National Cancer Institute (NCI) in longitudinal multiyear studies. NCI, together with the National Library of Medicine (NLM), is developing a unique web-accessible database of the digitized cervix images to study the evolution of lesions related to cervical cancer. Tools are needed for automated analysis of the cervigram content to support cancer research. We present a multistage scheme for segmenting and labeling regions of anatomical interest within the cervigrams. In particular, we focus on the extraction of the cervix region and fine detection of the cervix boundary; specular reflection is eliminated as an important preprocessing step; in addition, the entrance to the endocervical canal (the os), is detected. Segmentation results are evaluated on three image sets of cervigrams that were manually labeled by NCI experts.

Original language	English
Pages (from-to)	454-468
Number of pages	15
Journal	IEEE Transactions on Medical Imaging
Volume	28
Issue number	3
DOIs	https://doi.org/10.1109/TMI.2008.2007823
State	Published - Mar 2009

Funding

Funders
National Institutes of Health
U.S. National Library of Medicine
Lister Hill National Center for Biomedical Communications

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Cervical cancer
Curvature features
Image segmentation
Landmark extraction
Medical image analysis

Access to Document

10.1109/TMI.2008.2007823

Cite this

@article{118f321498914e7ea0790ce7226d5be9,

title = "Automatic detection of anatomical landmarks in uterine cervix images",

abstract = "The work focuses on a unique medical repository of digital cervicographic images (Cervigrams) collected by the National Cancer Institute (NCI) in longitudinal multiyear studies. NCI, together with the National Library of Medicine (NLM), is developing a unique web-accessible database of the digitized cervix images to study the evolution of lesions related to cervical cancer. Tools are needed for automated analysis of the cervigram content to support cancer research. We present a multistage scheme for segmenting and labeling regions of anatomical interest within the cervigrams. In particular, we focus on the extraction of the cervix region and fine detection of the cervix boundary; specular reflection is eliminated as an important preprocessing step; in addition, the entrance to the endocervical canal (the os), is detected. Segmentation results are evaluated on three image sets of cervigrams that were manually labeled by NCI experts.",

keywords = "Cervical cancer, Curvature features, Image segmentation, Landmark extraction, Medical image analysis",

author = "Hayit Greenspan and Shiri Gordon and Gali Zimmerman and Shelly Lotenberg and Jose Jeronimo and Sameer Antani and Rodney Long",

note = "Funding Information: Manuscript received June 19, 2008; revised September 19, 2008. First published October 31, 2008; current version published February 25, 2009. This research was supported in part by the Intramural Research Program of the National Institutes of Health (NIH), National Library of Medicine (NLM), and Lister Hill National Center for Biomedical Communications (LHNCBC).Asterisk indicates corresponding author. *H. Greenspan is with the Department of Biomedical Engineering, Faculty of Engineering, Tel-Aviv University, Ramat-Aviv 69978, Israel (e-mail: [email protected]).",

year = "2009",

month = mar,

doi = "10.1109/TMI.2008.2007823",

language = "אנגלית",

volume = "28",

pages = "454--468",

journal = "IEEE Transactions on Medical Imaging",

issn = "0278-0062",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "3",

}

TY - JOUR

T1 - Automatic detection of anatomical landmarks in uterine cervix images

AU - Greenspan, Hayit

AU - Gordon, Shiri

AU - Zimmerman, Gali

AU - Lotenberg, Shelly

AU - Jeronimo, Jose

AU - Antani, Sameer

AU - Long, Rodney

N1 - Funding Information: Manuscript received June 19, 2008; revised September 19, 2008. First published October 31, 2008; current version published February 25, 2009. This research was supported in part by the Intramural Research Program of the National Institutes of Health (NIH), National Library of Medicine (NLM), and Lister Hill National Center for Biomedical Communications (LHNCBC).Asterisk indicates corresponding author. *H. Greenspan is with the Department of Biomedical Engineering, Faculty of Engineering, Tel-Aviv University, Ramat-Aviv 69978, Israel (e-mail: [email protected]).

PY - 2009/3

Y1 - 2009/3

N2 - The work focuses on a unique medical repository of digital cervicographic images (Cervigrams) collected by the National Cancer Institute (NCI) in longitudinal multiyear studies. NCI, together with the National Library of Medicine (NLM), is developing a unique web-accessible database of the digitized cervix images to study the evolution of lesions related to cervical cancer. Tools are needed for automated analysis of the cervigram content to support cancer research. We present a multistage scheme for segmenting and labeling regions of anatomical interest within the cervigrams. In particular, we focus on the extraction of the cervix region and fine detection of the cervix boundary; specular reflection is eliminated as an important preprocessing step; in addition, the entrance to the endocervical canal (the os), is detected. Segmentation results are evaluated on three image sets of cervigrams that were manually labeled by NCI experts.

AB - The work focuses on a unique medical repository of digital cervicographic images (Cervigrams) collected by the National Cancer Institute (NCI) in longitudinal multiyear studies. NCI, together with the National Library of Medicine (NLM), is developing a unique web-accessible database of the digitized cervix images to study the evolution of lesions related to cervical cancer. Tools are needed for automated analysis of the cervigram content to support cancer research. We present a multistage scheme for segmenting and labeling regions of anatomical interest within the cervigrams. In particular, we focus on the extraction of the cervix region and fine detection of the cervix boundary; specular reflection is eliminated as an important preprocessing step; in addition, the entrance to the endocervical canal (the os), is detected. Segmentation results are evaluated on three image sets of cervigrams that were manually labeled by NCI experts.

KW - Cervical cancer

KW - Curvature features

KW - Image segmentation

KW - Landmark extraction

KW - Medical image analysis

UR - https://www.scopus.com/pages/publications/61549099002

U2 - 10.1109/TMI.2008.2007823

DO - 10.1109/TMI.2008.2007823

M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???

AN - SCOPUS:61549099002

SN - 0278-0062

VL - 28

SP - 454

EP - 468

JO - IEEE Transactions on Medical Imaging

JF - IEEE Transactions on Medical Imaging

IS - 3

ER -

Automatic detection of anatomical landmarks in uterine cervix images

Abstract

Funding

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this