Automatic Detection of Anatomical Landmarks in Uterine Cervix Images

Author

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

Author_Institution

Dept. of Biomed. Eng., Tel-Aviv Univ., Ramat-Aviv

Volume

28

Issue

3

fYear

2009

fDate

3/1/2009 12:00:00 AM

Firstpage

454

Lastpage

468

Abstract

The work focuses on a unique medical repository of digital cervicographic images (ldquoCervigramsrdquo) 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 ldquoosrdquo), is detected. Segmentation results are evaluated on three image sets of cervigrams that were manually labeled by NCI experts.

Keywords

biological organs; cancer; edge detection; feature extraction; gynaecology; image segmentation; medical image processing; tumours; NCI; NLM; National Cancer Institute; National Library of Medicine; Web-accessible database; automatic anatomical landmark detection; cervical cancer; cervigrams; cervix boundary detection; cervix region extraction; digital cervicographic images; endocervical canal; image preprocessing step; image segmentation; lesion evolution; regions-of-anatomical interest labeling; specular reflection; uterine cervix images; Biomedical engineering; Biomedical imaging; Cancer detection; Cervical cancer; Image databases; Image segmentation; Lesions; Medical diagnostic imaging; Medical treatment; Software libraries; Cervical cancer; curvature features; image segmentation; landmark extraction; medical image analysis; Algorithms; Cervix Uteri; Female; Humans; Image Interpretation, Computer-Assisted; Image Processing, Computer-Assisted; Information Storage and Retrieval; Normal Distribution; Pattern Recognition, Automated; Sensitivity and Specificity; Uterine Cervical Neoplasms;

fLanguage

English

Journal_Title

Medical Imaging, IEEE Transactions on

Publisher

ieee

ISSN

0278-0062

Type

jour

DOI

10.1109/TMI.2008.2007823

Filename

4663866