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. In 15th IEEE International Symposium on Biomedical Imaging. Washington: IEEE, 2018. p. 413-417. ISBN 978-1-5386-3636-7. doi:10.1109/ISBI.2018.8363605.
Other formats:   BibTeX LaTeX RIS
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
Original language English
Type of outcome Proceedings paper
Field of Study 10201 Computer sciences, information science, bioinformatics
Country of publisher United States of America
Confidentiality degree is not subject to a state or trade secret
Publication form electronic version available online
RIV identification code RIV/00216224:14330/18:00100837
Organization unit Faculty of Informatics
ISBN 978-1-5386-3636-7
ISSN 1945-7928
UT WoS 000455045600094
Keywords in English Cell segmentation; Convolutional Neural Networks; Chan-Vese model; Filopodia
Tags cbia-web, firank_B
Tags International impact, Reviewed
Changed by Changed by: RNDr. Pavel Šmerk, Ph.D., učo 3880. Changed: 29/4/2019 14:54.
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.
GJ16-03909Y, research and development projectName: Vývoj spolehlivých metod pro automatizovanou kvantitativní charakterizaci buněčné motility ve fluorescenční mikroskopii
Investor: Czech Science Foundation, Junior projects
PrintDisplayed: 22/4/2021 21:46