3-D Quantification of Filopodia in Motile Cancer Cells

J 2019

3-D Quantification of Filopodia in Motile Cancer Cells

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

Basic information

Original name

3-D Quantification of Filopodia in Motile Cancer Cells

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-SOLÓRZANO (724 Spain)

Edition

IEEE Transactions on Medical Imaging, IEEE, 2019, 0278-0062

Other information

Language

English

Type of outcome

Článek v odborném periodiku

Field of Study

10201 Computer sciences, information science, bioinformatics

Country of publisher

United States of America

Confidentiality degree

není předmětem státního či obchodního tajemství

References:

URL

Impact factor

Impact factor: 6.685

RIV identification code

RIV/00216224:14330/19:00107178

Organization unit

Faculty of Informatics

DOI

http://dx.doi.org/10.1109/TMI.2018.2873842

UT WoS

000460662400019

Keywords in English

Filopodium segmentation and tracking;actin cytoskeleton;confocal microscopy;3D skeletonization;Chan-Vese model;convolutional neural network;deep learning

Abstract

V originále

We present a 3D bioimage analysis workflow to quantitatively analyze single, actin-stained cells with filopodial protrusions of diverse structural and temporal attributes, such as number, length, thickness, level of branching, and lifetime, in time-lapse confocal microscopy image data. Our workflow makes use of convolutional neural networks trained using real as well as synthetic image data, to segment the cell volumes with highly heterogeneous fluorescence intensity levels and to detect individual filopodial protrusions, followed by a constrained nearest-neighbor tracking algorithm to obtain valuable information about the spatio-temporal evolution of individual filopodia. We validated the workflow using real and synthetic 3-D time-lapse sequences of lung adenocarcinoma cells of three morphologically distinct filopodial phenotypes and show that it achieves reliable segmentation and tracking performance, providing a robust, reproducible and less time-consuming alternative to manual analysis of the 3D+t image data.

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-SOLÓRZANO. 3-D Quantification of Filopodia in Motile Cancer Cells. IEEE Transactions on Medical Imaging. IEEE, 2019, vol. 38, No 3, p. 862-872. ISSN 0278-0062. Available from: https://dx.doi.org/10.1109/TMI.2018.2873842.

@article{1442158,
   author = {Castilla, Carlos and Maška, Martin and Sorokin, Dmitry and Meijering, Erik and OrtizanddeandSolórzano, Carlos},
   article_number = {3},
   doi = {http://dx.doi.org/10.1109/TMI.2018.2873842},
   keywords = {Filopodium segmentation and tracking;actin cytoskeleton;confocal microscopy;3D skeletonization;Chan-Vese model;convolutional neural network;deep learning},
   language = {eng},
   issn = {0278-0062},
   journal = {IEEE Transactions on Medical Imaging},
   title = {3-D Quantification of Filopodia in Motile Cancer Cells},
   url = {https://doi.org/10.1109/TMI.2018.2873842},
   volume = {38},
   year = {2019}
}

TY  - JOUR
ID  - 1442158
AU  - Castilla, Carlos - Maška, Martin - Sorokin, Dmitry - Meijering, Erik - Ortiz-de-Solórzano, Carlos
PY  - 2019
TI  - 3-D Quantification of Filopodia in Motile Cancer Cells
JF  - IEEE Transactions on Medical Imaging
VL  - 38
IS  - 3
SP  - 862-872
EP  - 862-872
PB  - IEEE
SN  - 02780062
KW  - Filopodium segmentation and tracking;actin cytoskeleton;confocal microscopy;3D skeletonization;Chan-Vese model;convolutional neural network;deep learning
UR  - https://doi.org/10.1109/TMI.2018.2873842
L2  - https://doi.org/10.1109/TMI.2018.2873842
N2  - We present a 3D bioimage analysis workflow to quantitatively analyze single, actin-stained cells with filopodial protrusions of diverse structural and temporal attributes, such as number, length, thickness, level of branching, and lifetime, in time-lapse confocal microscopy image data. Our workflow makes use of convolutional neural networks trained using real as well as synthetic image data, to segment the cell volumes with highly heterogeneous fluorescence intensity levels and to detect individual filopodial protrusions, followed by a constrained nearest-neighbor tracking algorithm to obtain valuable information about the spatio-temporal evolution of individual filopodia. We validated the workflow using real and synthetic 3-D time-lapse sequences of lung adenocarcinoma cells of three morphologically distinct filopodial phenotypes and show that it achieves reliable segmentation and tracking performance, providing a robust, reproducible and less time-consuming alternative to manual analysis of the 3D+t image data.
ER  -

CASTILLA, Carlos, Martin MAŠKA, Dmitry SOROKIN, Erik MEIJERING and Carlos ORTIZ-DE-SOLÓRZANO. 3-D Quantification of Filopodia in Motile Cancer Cells. \textit{IEEE Transactions on Medical Imaging}. IEEE, 2019, vol.~38, No~3, p.~862-872. ISSN~0278-0062. Available from: https://dx.doi.org/10.1109/TMI.2018.2873842.

Detailed Information on Publication Record