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.

Základní údaje

Originální název

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

Autoři

CASTILLA, Carlos; Martin MAŠKA ; Dmitry SOROKIN; Erik MEIJERING a Carlos ORTIZ-DE-SOLORZANO

Vydání

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

Nakladatel

IEEE

Další údaje

Jazyk

angličtina

Typ výsledku

Stať ve sborníku

Obor

10201 Computer sciences, information science, bioinformatics

Stát vydavatele

Spojené státy

Utajení

není předmětem státního či obchodního tajemství

Forma vydání

elektronická verze "online"

Odkazy

URL

Označené pro přenos do RIV

Ano

Kód RIV

RIV/00216224:14330/18:00100837

Organizační jednotka

Fakulta informatiky

ISBN

978-1-5386-3636-7

ISSN

Klíčová slova anglicky

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

Štítky

cbia-web, firank_B

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 29. 4. 2019 14:54, RNDr. Pavel Šmerk, Ph.D.

Anotace

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.

Návaznosti

GJ16-03909Y, projekt VaV

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

Investor: Grantová agentura ČR, Vývoj spolehlivých metod pro automatizovanou kvantitativní charakterizaci buněčné motility ve fluorescenční mikroskopii

Citovat

CASTILLA, Carlos; Martin MAŠKA; Dmitry SOROKIN; Erik MEIJERING a 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, s. 413-417. ISBN 978-1-5386-3636-7. Dostupné z: https://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 = {https://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  - CONF
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 a 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, s.~413-417. ISBN~978-1-5386-3636-7. Dostupné z: https://doi.org/10.1109/ISBI.2018.8363605.

Přehled o publikaci