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

Warning

This publication doesn't include Faculty of Arts. It includes Faculty of Informatics. Official publication website can be found on muni.cz.
Authors

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

Year of publication 2018
Type Article in Proceedings
Conference 15th IEEE International Symposium on Biomedical Imaging
MU Faculty or unit

Faculty of Informatics

Citation
Web https://doi.org/10.1109/ISBI.2018.8363605
Doi http://dx.doi.org/10.1109/ISBI.2018.8363605
Keywords Cell segmentation; Convolutional Neural Networks; Chan-Vese model; Filopodia
Description 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.
Related projects:

You are running an old browser version. We recommend updating your browser to its latest version.