Segmentation of cervical cell nuclei in high-resolution microscopic images: A new algorithm and a web-based software framework

Christoph Bergmeir, Miguel García Silvente, José Manuel Benítez

Research output: Contribution to journalArticleResearchpeer-review

Abstract

In order to automate cervical cancer screening tests, one of the most important and longstanding challenges is the segmentation of cell nuclei in the stained specimens. Though nuclei of isolated cells in high-quality acquisitions often are easy to segment, the problem lies in the segmentation of large numbers of nuclei with various characteristics under differing acquisition conditions in high-resolution scans of the complete microscope slides. We implemented a system that enables processing of full resolution images, and proposes a new algorithm for segmenting the nuclei under adequate control of the expert user. The system can work automatically or interactively guided, to allow for segmentation within the whole range of slide and image characteristics. It facilitates data storage and interaction of technical and medical experts, especially with its web-based architecture. The proposed algorithm localizes cell nuclei using a voting scheme and prior knowledge, before it determines the exact shape of the nuclei by means of an elastic segmentation algorithm. After noise removal with a mean-shift and a median filtering takes place, edges are extracted with a Canny edge detection algorithm. Motivated by the observation that cell nuclei are surrounded by cytoplasm and their shape is roughly elliptical, edges adjacent to the background are removed. A randomized Hough transform for ellipses finds candidate nuclei, which are then processed by a level set algorithm. The algorithm is tested and compared to other algorithms on a database containing 207 images acquired from two different microscope slides, with promising results.

Original languageEnglish
Pages (from-to)497-512
Number of pages16
JournalComputer Methods and Programs in Biomedicine
Volume107
Issue number3
DOIs
Publication statusPublished - Sep 2012
Externally publishedYes

Keywords

  • Cervical cell imaging
  • High-resolution microscopic imaging
  • Nucleus segmentation

Cite this

@article{4e19ea36121d4516bc9c6b389cd49d2f,
title = "Segmentation of cervical cell nuclei in high-resolution microscopic images: A new algorithm and a web-based software framework",
abstract = "In order to automate cervical cancer screening tests, one of the most important and longstanding challenges is the segmentation of cell nuclei in the stained specimens. Though nuclei of isolated cells in high-quality acquisitions often are easy to segment, the problem lies in the segmentation of large numbers of nuclei with various characteristics under differing acquisition conditions in high-resolution scans of the complete microscope slides. We implemented a system that enables processing of full resolution images, and proposes a new algorithm for segmenting the nuclei under adequate control of the expert user. The system can work automatically or interactively guided, to allow for segmentation within the whole range of slide and image characteristics. It facilitates data storage and interaction of technical and medical experts, especially with its web-based architecture. The proposed algorithm localizes cell nuclei using a voting scheme and prior knowledge, before it determines the exact shape of the nuclei by means of an elastic segmentation algorithm. After noise removal with a mean-shift and a median filtering takes place, edges are extracted with a Canny edge detection algorithm. Motivated by the observation that cell nuclei are surrounded by cytoplasm and their shape is roughly elliptical, edges adjacent to the background are removed. A randomized Hough transform for ellipses finds candidate nuclei, which are then processed by a level set algorithm. The algorithm is tested and compared to other algorithms on a database containing 207 images acquired from two different microscope slides, with promising results.",
keywords = "Cervical cell imaging, High-resolution microscopic imaging, Nucleus segmentation",
author = "Christoph Bergmeir and {Garc{\'i}a Silvente}, Miguel and Ben{\'i}tez, {Jos{\'e} Manuel}",
year = "2012",
month = "9",
doi = "10.1016/j.cmpb.2011.09.017",
language = "English",
volume = "107",
pages = "497--512",
journal = "Computer Methods and Programs in Biomedicine",
issn = "0169-2607",
publisher = "Elsevier",
number = "3",

}

Segmentation of cervical cell nuclei in high-resolution microscopic images : A new algorithm and a web-based software framework. / Bergmeir, Christoph; García Silvente, Miguel; Benítez, José Manuel.

In: Computer Methods and Programs in Biomedicine, Vol. 107, No. 3, 09.2012, p. 497-512.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Segmentation of cervical cell nuclei in high-resolution microscopic images

T2 - A new algorithm and a web-based software framework

AU - Bergmeir, Christoph

AU - García Silvente, Miguel

AU - Benítez, José Manuel

PY - 2012/9

Y1 - 2012/9

N2 - In order to automate cervical cancer screening tests, one of the most important and longstanding challenges is the segmentation of cell nuclei in the stained specimens. Though nuclei of isolated cells in high-quality acquisitions often are easy to segment, the problem lies in the segmentation of large numbers of nuclei with various characteristics under differing acquisition conditions in high-resolution scans of the complete microscope slides. We implemented a system that enables processing of full resolution images, and proposes a new algorithm for segmenting the nuclei under adequate control of the expert user. The system can work automatically or interactively guided, to allow for segmentation within the whole range of slide and image characteristics. It facilitates data storage and interaction of technical and medical experts, especially with its web-based architecture. The proposed algorithm localizes cell nuclei using a voting scheme and prior knowledge, before it determines the exact shape of the nuclei by means of an elastic segmentation algorithm. After noise removal with a mean-shift and a median filtering takes place, edges are extracted with a Canny edge detection algorithm. Motivated by the observation that cell nuclei are surrounded by cytoplasm and their shape is roughly elliptical, edges adjacent to the background are removed. A randomized Hough transform for ellipses finds candidate nuclei, which are then processed by a level set algorithm. The algorithm is tested and compared to other algorithms on a database containing 207 images acquired from two different microscope slides, with promising results.

AB - In order to automate cervical cancer screening tests, one of the most important and longstanding challenges is the segmentation of cell nuclei in the stained specimens. Though nuclei of isolated cells in high-quality acquisitions often are easy to segment, the problem lies in the segmentation of large numbers of nuclei with various characteristics under differing acquisition conditions in high-resolution scans of the complete microscope slides. We implemented a system that enables processing of full resolution images, and proposes a new algorithm for segmenting the nuclei under adequate control of the expert user. The system can work automatically or interactively guided, to allow for segmentation within the whole range of slide and image characteristics. It facilitates data storage and interaction of technical and medical experts, especially with its web-based architecture. The proposed algorithm localizes cell nuclei using a voting scheme and prior knowledge, before it determines the exact shape of the nuclei by means of an elastic segmentation algorithm. After noise removal with a mean-shift and a median filtering takes place, edges are extracted with a Canny edge detection algorithm. Motivated by the observation that cell nuclei are surrounded by cytoplasm and their shape is roughly elliptical, edges adjacent to the background are removed. A randomized Hough transform for ellipses finds candidate nuclei, which are then processed by a level set algorithm. The algorithm is tested and compared to other algorithms on a database containing 207 images acquired from two different microscope slides, with promising results.

KW - Cervical cell imaging

KW - High-resolution microscopic imaging

KW - Nucleus segmentation

UR - http://www.scopus.com/inward/record.url?scp=84863869463&partnerID=8YFLogxK

U2 - 10.1016/j.cmpb.2011.09.017

DO - 10.1016/j.cmpb.2011.09.017

M3 - Article

VL - 107

SP - 497

EP - 512

JO - Computer Methods and Programs in Biomedicine

JF - Computer Methods and Programs in Biomedicine

SN - 0169-2607

IS - 3

ER -