Accurate Morphology Preserving Segmentation of Overlapping Cells based on Active Contours

Csaba Molnar, Ian H. Jermyn, Z. Kato, Vesa Rahkama, Païvi Östling, Piia Mikkonen, Vilja Pietiaïnen, Peter Horvath

Research output: Contribution to journalArticle

19 Citations (Scopus)

Abstract

The identification of fluorescently stained cell nuclei is the basis of cell detection, segmentation, and feature extraction in high content microscopy experiments. The nuclear morphology of single cells is also one of the essential indicators of phenotypic variation. However, the cells used in experiments can lose their contact inhibition, and can therefore pile up on top of each other, making the detection of single cells extremely challenging using current segmentation methods. The model we present here can detect cell nuclei and their morphology even in high-confluency cell cultures with many overlapping cell nuclei. We combine the "gas of near circles" active contour model, which favors circular shapes but allows slight variations around them, with a new data model. This captures a common property of many microscopic imaging techniques: the intensities from superposed nuclei are additive, so that two overlapping nuclei, for example, have a total intensity that is approximately double the intensity of a single nucleus. We demonstrate the power of our method on microscopic images of cells, comparing the results with those obtained from a widely used approach, and with manual image segmentations by experts.

Original languageEnglish
Article number32412
JournalScientific Reports
Volume6
DOIs
Publication statusPublished - Aug 26 2016

Fingerprint

Cell Nucleus
Contact Inhibition
Microscopy
Cell Culture Techniques
Gases

ASJC Scopus subject areas

  • General

Cite this

Molnar, C., Jermyn, I. H., Kato, Z., Rahkama, V., Östling, P., Mikkonen, P., ... Horvath, P. (2016). Accurate Morphology Preserving Segmentation of Overlapping Cells based on Active Contours. Scientific Reports, 6, [32412]. https://doi.org/10.1038/srep32412

Accurate Morphology Preserving Segmentation of Overlapping Cells based on Active Contours. / Molnar, Csaba; Jermyn, Ian H.; Kato, Z.; Rahkama, Vesa; Östling, Païvi; Mikkonen, Piia; Pietiaïnen, Vilja; Horvath, Peter.

In: Scientific Reports, Vol. 6, 32412, 26.08.2016.

Research output: Contribution to journalArticle

Molnar, C, Jermyn, IH, Kato, Z, Rahkama, V, Östling, P, Mikkonen, P, Pietiaïnen, V & Horvath, P 2016, 'Accurate Morphology Preserving Segmentation of Overlapping Cells based on Active Contours', Scientific Reports, vol. 6, 32412. https://doi.org/10.1038/srep32412
Molnar, Csaba ; Jermyn, Ian H. ; Kato, Z. ; Rahkama, Vesa ; Östling, Païvi ; Mikkonen, Piia ; Pietiaïnen, Vilja ; Horvath, Peter. / Accurate Morphology Preserving Segmentation of Overlapping Cells based on Active Contours. In: Scientific Reports. 2016 ; Vol. 6.
@article{ad66643cfb994f61ad2ca9235fd055fb,
title = "Accurate Morphology Preserving Segmentation of Overlapping Cells based on Active Contours",
abstract = "The identification of fluorescently stained cell nuclei is the basis of cell detection, segmentation, and feature extraction in high content microscopy experiments. The nuclear morphology of single cells is also one of the essential indicators of phenotypic variation. However, the cells used in experiments can lose their contact inhibition, and can therefore pile up on top of each other, making the detection of single cells extremely challenging using current segmentation methods. The model we present here can detect cell nuclei and their morphology even in high-confluency cell cultures with many overlapping cell nuclei. We combine the {"}gas of near circles{"} active contour model, which favors circular shapes but allows slight variations around them, with a new data model. This captures a common property of many microscopic imaging techniques: the intensities from superposed nuclei are additive, so that two overlapping nuclei, for example, have a total intensity that is approximately double the intensity of a single nucleus. We demonstrate the power of our method on microscopic images of cells, comparing the results with those obtained from a widely used approach, and with manual image segmentations by experts.",
author = "Csaba Molnar and Jermyn, {Ian H.} and Z. Kato and Vesa Rahkama and Pa{\"i}vi {\"O}stling and Piia Mikkonen and Vilja Pietia{\"i}nen and Peter Horvath",
year = "2016",
month = "8",
day = "26",
doi = "10.1038/srep32412",
language = "English",
volume = "6",
journal = "Scientific Reports",
issn = "2045-2322",
publisher = "Nature Publishing Group",

}

TY - JOUR

T1 - Accurate Morphology Preserving Segmentation of Overlapping Cells based on Active Contours

AU - Molnar, Csaba

AU - Jermyn, Ian H.

AU - Kato, Z.

AU - Rahkama, Vesa

AU - Östling, Païvi

AU - Mikkonen, Piia

AU - Pietiaïnen, Vilja

AU - Horvath, Peter

PY - 2016/8/26

Y1 - 2016/8/26

N2 - The identification of fluorescently stained cell nuclei is the basis of cell detection, segmentation, and feature extraction in high content microscopy experiments. The nuclear morphology of single cells is also one of the essential indicators of phenotypic variation. However, the cells used in experiments can lose their contact inhibition, and can therefore pile up on top of each other, making the detection of single cells extremely challenging using current segmentation methods. The model we present here can detect cell nuclei and their morphology even in high-confluency cell cultures with many overlapping cell nuclei. We combine the "gas of near circles" active contour model, which favors circular shapes but allows slight variations around them, with a new data model. This captures a common property of many microscopic imaging techniques: the intensities from superposed nuclei are additive, so that two overlapping nuclei, for example, have a total intensity that is approximately double the intensity of a single nucleus. We demonstrate the power of our method on microscopic images of cells, comparing the results with those obtained from a widely used approach, and with manual image segmentations by experts.

AB - The identification of fluorescently stained cell nuclei is the basis of cell detection, segmentation, and feature extraction in high content microscopy experiments. The nuclear morphology of single cells is also one of the essential indicators of phenotypic variation. However, the cells used in experiments can lose their contact inhibition, and can therefore pile up on top of each other, making the detection of single cells extremely challenging using current segmentation methods. The model we present here can detect cell nuclei and their morphology even in high-confluency cell cultures with many overlapping cell nuclei. We combine the "gas of near circles" active contour model, which favors circular shapes but allows slight variations around them, with a new data model. This captures a common property of many microscopic imaging techniques: the intensities from superposed nuclei are additive, so that two overlapping nuclei, for example, have a total intensity that is approximately double the intensity of a single nucleus. We demonstrate the power of our method on microscopic images of cells, comparing the results with those obtained from a widely used approach, and with manual image segmentations by experts.

UR - http://www.scopus.com/inward/record.url?scp=84983804197&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84983804197&partnerID=8YFLogxK

U2 - 10.1038/srep32412

DO - 10.1038/srep32412

M3 - Article

C2 - 27561654

AN - SCOPUS:84983804197

VL - 6

JO - Scientific Reports

JF - Scientific Reports

SN - 2045-2322

M1 - 32412

ER -