Segmentation of Actin-Stained 3D Fluorescent Cells with
Filopodial Protrusions using Convolutional Neural Networks

D 2018

Segmentation of Actin-Stained 3D Fluorescent Cells with Filopodial Protrusions using Convolutional Neural Networks

CASTILLA, Carlos, Martin MAŠKA, Dmitry SOROKIN, Erik MEIJERING, Carlos ORTIZ-DE-SOLORZANO et. al.

Basic information

Original name

Segmentation of Actin-Stained 3D Fluorescent Cells with Filopodial Protrusions using Convolutional Neural Networks

Authors

CASTILLA, Carlos (724 Spain), Martin MAŠKA (203 Czech Republic, guarantor, belonging to the institution), Dmitry SOROKIN (643 Russian Federation, belonging to the institution), Erik MEIJERING (528 Netherlands) and Carlos ORTIZ-DE-SOLORZANO (724 Spain)

Edition

Washington, 15th IEEE International Symposium on Biomedical Imaging, p. 413-417, 5 pp. 2018

Publisher

IEEE

Other information

Language

English

Type of outcome

Stať ve sborníku

Field of Study

10201 Computer sciences, information science, bioinformatics

Country of publisher

United States of America

Confidentiality degree

není předmětem státního či obchodního tajemství

Publication form

electronic version available online

References:

URL

RIV identification code

RIV/00216224:14330/18:00100837

Organization unit

Faculty of Informatics

ISBN

978-1-5386-3636-7

ISSN

DOI

http://dx.doi.org/10.1109/ISBI.2018.8363605

UT WoS

000455045600094

Keywords in English

Cell segmentation; Convolutional Neural Networks; Chan-Vese model; Filopodia

Abstract

V originále

We present the architecture, training strategy and evaluation of a convolutional neural network (CNN) designed for the segmentation of actin-stained cells in 3D+t confocal microscopy image data. The segmentation performance of the CNN is evaluated using time-lapse sequences of lung adenocarcinoma cells with three genetically distinct variants of the tubulin adaptor protein, a key protein in the process of assembly of the cell cytoskeleton, displaying three different phenotypes in regards to the morphology of the cells and in particular, to the number and length of filopodial structures. We show that the CNN significantly outperforms a baseline method based on the minimization of the Chan-Vese model using graph cuts, and we discuss the inherent benefits of using the CNN over the baseline method.

Links

GJ16-03909Y, research and development project

Name: Vývoj spolehlivých metod pro automatizovanou kvantitativní charakterizaci buněčné motility ve fluorescenční mikroskopii

Investor: Czech Science Foundation

Citovat

CASTILLA, Carlos, Martin MAŠKA, Dmitry SOROKIN, Erik MEIJERING and Carlos ORTIZ-DE-SOLORZANO. Segmentation of Actin-Stained 3D Fluorescent Cells with Filopodial Protrusions using Convolutional Neural Networks. Online. In 15th IEEE International Symposium on Biomedical Imaging. Washington: IEEE, 2018, p. 413-417. ISBN 978-1-5386-3636-7. Available from: https://dx.doi.org/10.1109/ISBI.2018.8363605.

@inproceedings{1409298,
   author = {Castilla, Carlos and Maška, Martin and Sorokin, Dmitry and Meijering, Erik and OrtizanddeandSolorzano, Carlos},
   address = {Washington},
   booktitle = {15th IEEE International Symposium on Biomedical Imaging},
   doi = {http://dx.doi.org/10.1109/ISBI.2018.8363605},
   keywords = {Cell segmentation; Convolutional Neural Networks; Chan-Vese model; Filopodia},
   howpublished = {elektronická verze "online"},
   language = {eng},
   location = {Washington},
   isbn = {978-1-5386-3636-7},
   pages = {413-417},
   publisher = {IEEE},
   title = {Segmentation of Actin-Stained 3D Fluorescent Cells with Filopodial Protrusions using Convolutional Neural Networks},
   url = {https://doi.org/10.1109/ISBI.2018.8363605},
   year = {2018}
}

TY  - JOUR
ID  - 1409298
AU  - Castilla, Carlos - Maška, Martin - Sorokin, Dmitry - Meijering, Erik - Ortiz-de-Solorzano, Carlos
PY  - 2018
TI  - Segmentation of Actin-Stained 3D Fluorescent Cells with Filopodial Protrusions using Convolutional Neural Networks
PB  - IEEE
CY  - Washington
SN  - 9781538636367
KW  - Cell segmentation
KW  - Convolutional Neural Networks
KW  - Chan-Vese model
KW  - Filopodia
UR  - https://doi.org/10.1109/ISBI.2018.8363605
N2  - We present the architecture, training strategy and evaluation of a convolutional neural network (CNN) designed for the segmentation of actin-stained cells in 3D+t confocal microscopy image data. The segmentation performance of the CNN is evaluated using time-lapse sequences of lung adenocarcinoma cells with three genetically distinct variants of the tubulin adaptor protein, a key protein in the process of assembly of the cell cytoskeleton, displaying three different phenotypes in regards to the morphology of the cells and in particular, to the number and length of filopodial structures. We show that the CNN significantly outperforms a baseline method based on the minimization of the Chan-Vese model using graph cuts, and we discuss the inherent benefits of using the CNN over the baseline method.
ER  -

CASTILLA, Carlos, Martin MAŠKA, Dmitry SOROKIN, Erik MEIJERING and Carlos ORTIZ-DE-SOLORZANO. Segmentation of Actin-Stained 3D Fluorescent Cells with Filopodial Protrusions using Convolutional Neural Networks. Online. In \textit{15th IEEE International Symposium on Biomedical Imaging}. Washington: IEEE, 2018, p.~413-417. ISBN~978-1-5386-3636-7. Available from: https://dx.doi.org/10.1109/ISBI.2018.8363605.

Detailed Information on Publication Record