Automated Cell Segmentation in Phase-Contrast Images based on
Classification and Region Growing

D 2015

Automated Cell Segmentation in Phase-Contrast Images based on Classification and Region Growing

STOKLASA, Roman, Lukáš BÁLEK, Pavel KREJČÍ and Petr MATULA

Basic information

Original name

Automated Cell Segmentation in Phase-Contrast Images based on Classification and Region Growing

Authors

STOKLASA, Roman (703 Slovakia, belonging to the institution), Lukáš BÁLEK (203 Czech Republic, belonging to the institution), Pavel KREJČÍ (203 Czech Republic, belonging to the institution) and Petr MATULA (203 Czech Republic, guarantor, belonging to the institution)

Edition

Neuveden, Proceedings of 2015 IEEE International Symposium on Biomedical Imaging, 2015. p. 1447-1451, 5 pp. 2015

Publisher

Engineering in Medicine and Biology Society

Other information

Language

English

Type of outcome

Stať ve sborníku

Field of Study

20200 2.2 Electrical engineering, Electronic engineering, Information engineering

Country of publisher

United States of America

Confidentiality degree

není předmětem státního či obchodního tajemství

Publication form

storage medium (CD, DVD, flash disk)

References:

URL

RIV identification code

RIV/00216224:14330/15:00082559

Organization unit

Faculty of Informatics

ISBN

978-1-4799-2374-8

ISSN

DOI

http://dx.doi.org/10.1109/ISBI.2015.7164149

UT WoS

000380546000348

Keywords in English

phase-contrast microscopy; segmentation; classification; superpixel; cells

Abstract

V originále

Cell segmentation in phase-contrast microscopy images remains a challenging problem because of the large variability in subcellular structures and imaging artifacts. In this paper, we present an approach to the automatic segmentation of tightly packed cells in phase-contrast images. We combine the classification of superpixels with the region-growing method to locate cell membrane boundaries. We demonstrate that such a combined approach is able to perform the task of cell detection and segmentation with a high level of precision. On the presented dataset, we achieved 90% precision with 78% recall. The results indicate that this method is suitable for real biological applications.

Links

MUNI/A/1159/2014, interní kód MU

Name: Rozsáhlé výpočetní systémy: modely, aplikace a verifikace IV.

Investor: Masaryk University, Category A

MUNI/A/1206/2014, interní kód MU

Name: Zapojení studentů Fakulty informatiky do mezinárodní vědecké komunity (Acronym: SKOMU)

Investor: Masaryk University, Category A

MUNI/M/0071/2013, interní kód MU

Name: High-throughput screening of compound libraries aimed on discovery of novel inhibitors of the FGFR/ERK MAP kinase signaling (Acronym: HTS-FGFR)

Investor: Masaryk University, INTERDISCIPLINARY - Interdisciplinary research projects

Citovat

STOKLASA, Roman, Lukáš BÁLEK, Pavel KREJČÍ and Petr MATULA. Automated Cell Segmentation in Phase-Contrast Images based on Classification and Region Growing. In Proceedings of 2015 IEEE International Symposium on Biomedical Imaging, 2015. Neuveden: Engineering in Medicine and Biology Society, 2015, p. 1447-1451. ISBN 978-1-4799-2374-8. Available from: https://dx.doi.org/10.1109/ISBI.2015.7164149.

@inproceedings{1230987,
   author = {Stoklasa, Roman and Bálek, Lukáš and Krejčí, Pavel and Matula, Petr},
   address = {Neuveden},
   booktitle = {Proceedings of 2015 IEEE International Symposium on Biomedical Imaging, 2015.},
   doi = {http://dx.doi.org/10.1109/ISBI.2015.7164149},
   keywords = {phase-contrast microscopy; segmentation; classification; superpixel; cells},
   howpublished = {paměťový nosič},
   language = {eng},
   location = {Neuveden},
   isbn = {978-1-4799-2374-8},
   pages = {1447-1451},
   publisher = {Engineering in Medicine and Biology Society},
   title = {Automated Cell Segmentation in Phase-Contrast Images based on Classification and Region Growing},
   url = {https://ieeexplore.ieee.org/document/7164149},
   year = {2015}
}

TY  - JOUR
ID  - 1230987
AU  - Stoklasa, Roman - Bálek, Lukáš - Krejčí, Pavel - Matula, Petr
PY  - 2015
TI  - Automated Cell Segmentation in Phase-Contrast Images based on Classification and Region Growing
PB  - Engineering in Medicine and Biology Society
CY  - Neuveden
SN  - 9781479923748
KW  - phase-contrast microscopy
KW  - segmentation
KW  - classification
KW  - superpixel
KW  - cells
UR  - https://ieeexplore.ieee.org/document/7164149
L2  - https://ieeexplore.ieee.org/document/7164149
N2  - Cell segmentation in phase-contrast microscopy images remains a challenging problem because of the large variability in subcellular structures and imaging artifacts. In this paper, we present an approach to the automatic segmentation of tightly packed cells in phase-contrast images. We combine the classification of superpixels with the region-growing method to locate cell membrane boundaries. We demonstrate that such a combined approach is able to perform the task of cell detection and segmentation with a high level of precision. On the presented dataset, we achieved 90% precision with 78% recall. The results indicate that this method is suitable for real biological applications.
ER  -

STOKLASA, Roman, Lukáš BÁLEK, Pavel KREJČÍ and Petr MATULA. Automated Cell Segmentation in Phase-Contrast Images based on Classification and Region Growing. In \textit{Proceedings of 2015 IEEE International Symposium on Biomedical Imaging, 2015.}. Neuveden: Engineering in Medicine and Biology Society, 2015, p.~1447-1451. ISBN~978-1-4799-2374-8. Available from: https://dx.doi.org/10.1109/ISBI.2015.7164149.

Detailed Information on Publication Record