Marker-controlled watershed segmentation of nuclei in H&E stained breast cancer biopsy images

M. Veta, A. Huisman, M. A. Viergever, P. J. Van Diest, J. P W Pluim

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

Abstract

In this paper we present an unsupervised automatic method for segmentation of nuclei in H&E stained breast cancer biopsy images. Colour deconvolution and morphological operations are used to preprocess the images in order to remove irrelevant structures. Candidate nuclei locations, obtained with the fast radial symmetry transform, act as markers for a marker-controlled watershed segmentation. Watershed regions that are unlikely to represent nuclei are removed in the postprocessing stage. The proposed algorithm is evaluated on a number of images that are representative of the diversity in pathology in this type of tissue. The method shows good performance in terms of the number of segmented nuclei and segmentation accuracy.

Original languageEnglish (US)
Title of host publicationProceedings - International Symposium on Biomedical Imaging
Pages618-621
Number of pages4
DOIs
StatePublished - 2011
Externally publishedYes
Event2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11 - Chicago, IL, United States
Duration: Mar 30 2011Apr 2 2011

Other

Other2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11
CountryUnited States
CityChicago, IL
Period3/30/114/2/11

Fingerprint

Biopsy
Watersheds
Breast Neoplasms
Pathology
Deconvolution
Color
Tissue

Keywords

  • breast cancer
  • histology images
  • Marker-controlled watershed
  • nuclei segmentation

ASJC Scopus subject areas

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging

Cite this

Veta, M., Huisman, A., Viergever, M. A., Van Diest, P. J., & Pluim, J. P. W. (2011). Marker-controlled watershed segmentation of nuclei in H&E stained breast cancer biopsy images. In Proceedings - International Symposium on Biomedical Imaging (pp. 618-621). [5872483] https://doi.org/10.1109/ISBI.2011.5872483

Marker-controlled watershed segmentation of nuclei in H&E stained breast cancer biopsy images. / Veta, M.; Huisman, A.; Viergever, M. A.; Van Diest, P. J.; Pluim, J. P W.

Proceedings - International Symposium on Biomedical Imaging. 2011. p. 618-621 5872483.

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

Veta, M, Huisman, A, Viergever, MA, Van Diest, PJ & Pluim, JPW 2011, Marker-controlled watershed segmentation of nuclei in H&E stained breast cancer biopsy images. in Proceedings - International Symposium on Biomedical Imaging., 5872483, pp. 618-621, 2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11, Chicago, IL, United States, 3/30/11. https://doi.org/10.1109/ISBI.2011.5872483
Veta M, Huisman A, Viergever MA, Van Diest PJ, Pluim JPW. Marker-controlled watershed segmentation of nuclei in H&E stained breast cancer biopsy images. In Proceedings - International Symposium on Biomedical Imaging. 2011. p. 618-621. 5872483 https://doi.org/10.1109/ISBI.2011.5872483
Veta, M. ; Huisman, A. ; Viergever, M. A. ; Van Diest, P. J. ; Pluim, J. P W. / Marker-controlled watershed segmentation of nuclei in H&E stained breast cancer biopsy images. Proceedings - International Symposium on Biomedical Imaging. 2011. pp. 618-621
@inproceedings{1dba25b7e8b44432b6cab7934419f6d1,
title = "Marker-controlled watershed segmentation of nuclei in H&E stained breast cancer biopsy images",
abstract = "In this paper we present an unsupervised automatic method for segmentation of nuclei in H&E stained breast cancer biopsy images. Colour deconvolution and morphological operations are used to preprocess the images in order to remove irrelevant structures. Candidate nuclei locations, obtained with the fast radial symmetry transform, act as markers for a marker-controlled watershed segmentation. Watershed regions that are unlikely to represent nuclei are removed in the postprocessing stage. The proposed algorithm is evaluated on a number of images that are representative of the diversity in pathology in this type of tissue. The method shows good performance in terms of the number of segmented nuclei and segmentation accuracy.",
keywords = "breast cancer, histology images, Marker-controlled watershed, nuclei segmentation",
author = "M. Veta and A. Huisman and Viergever, {M. A.} and {Van Diest}, {P. J.} and Pluim, {J. P W}",
year = "2011",
doi = "10.1109/ISBI.2011.5872483",
language = "English (US)",
isbn = "9781424441280",
pages = "618--621",
booktitle = "Proceedings - International Symposium on Biomedical Imaging",

}

TY - GEN

T1 - Marker-controlled watershed segmentation of nuclei in H&E stained breast cancer biopsy images

AU - Veta, M.

AU - Huisman, A.

AU - Viergever, M. A.

AU - Van Diest, P. J.

AU - Pluim, J. P W

PY - 2011

Y1 - 2011

N2 - In this paper we present an unsupervised automatic method for segmentation of nuclei in H&E stained breast cancer biopsy images. Colour deconvolution and morphological operations are used to preprocess the images in order to remove irrelevant structures. Candidate nuclei locations, obtained with the fast radial symmetry transform, act as markers for a marker-controlled watershed segmentation. Watershed regions that are unlikely to represent nuclei are removed in the postprocessing stage. The proposed algorithm is evaluated on a number of images that are representative of the diversity in pathology in this type of tissue. The method shows good performance in terms of the number of segmented nuclei and segmentation accuracy.

AB - In this paper we present an unsupervised automatic method for segmentation of nuclei in H&E stained breast cancer biopsy images. Colour deconvolution and morphological operations are used to preprocess the images in order to remove irrelevant structures. Candidate nuclei locations, obtained with the fast radial symmetry transform, act as markers for a marker-controlled watershed segmentation. Watershed regions that are unlikely to represent nuclei are removed in the postprocessing stage. The proposed algorithm is evaluated on a number of images that are representative of the diversity in pathology in this type of tissue. The method shows good performance in terms of the number of segmented nuclei and segmentation accuracy.

KW - breast cancer

KW - histology images

KW - Marker-controlled watershed

KW - nuclei segmentation

UR - http://www.scopus.com/inward/record.url?scp=80055035411&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80055035411&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2011.5872483

DO - 10.1109/ISBI.2011.5872483

M3 - Conference contribution

SN - 9781424441280

SP - 618

EP - 621

BT - Proceedings - International Symposium on Biomedical Imaging

ER -