TU Darmstadt / ULB / TUbiblio

Multiclass Yeast Segmentation in Microstructured Environments with Deep Learning

Prangemeier, T. and Wildner, C. and Francani, A. O. and Reich, C. and Koeppl, H. (2020):
Multiclass Yeast Segmentation in Microstructured Environments with Deep Learning.
IEEE, In: International Conference on Computational Intelligence in Bioinformatics and Computational Biology, virtual Conference, October 27-29, 2020, [Online-Edition: https://www.bcs.tu-darmstadt.de/media/bcs/research_4/documen...],
[Conference or Workshop Item]

Abstract

Cell segmentation is a major bottleneck in extracting quantitative single-cell information from microscopy data. The challenge is exasperated in the setting of microstructured environments. While deep learning approaches have proven useful for general cell segmentation tasks, existing segmentation tools for the yeast-microstructure setting rely on traditional machine learning approaches. Here we present convolutional neural networks trained for multiclass segmenting of individual yeast cells and discerning these from cell-similar microstructures. We give an overview of the datasets recorded for training, validating and testing the networks, as well as a typical usecase. We showcase the method’s contribution to segmenting yeast in microstructured environments with a typical synthetic biology application in mind. The models achieve robust segmentation results, outperforming the previous state-of-the-art in both accuracy and speed. The combination of fast and accurate segmentation is not only beneficial for a posteriori data processing, it also makes online monitoring of thousands of trapped cells or closed-loop optimal experimental design feasible from an image processing perspective.

Item Type: Conference or Workshop Item
Erschienen: 2020
Creators: Prangemeier, T. and Wildner, C. and Francani, A. O. and Reich, C. and Koeppl, H.
Title: Multiclass Yeast Segmentation in Microstructured Environments with Deep Learning
Language: English
Abstract:

Cell segmentation is a major bottleneck in extracting quantitative single-cell information from microscopy data. The challenge is exasperated in the setting of microstructured environments. While deep learning approaches have proven useful for general cell segmentation tasks, existing segmentation tools for the yeast-microstructure setting rely on traditional machine learning approaches. Here we present convolutional neural networks trained for multiclass segmenting of individual yeast cells and discerning these from cell-similar microstructures. We give an overview of the datasets recorded for training, validating and testing the networks, as well as a typical usecase. We showcase the method’s contribution to segmenting yeast in microstructured environments with a typical synthetic biology application in mind. The models achieve robust segmentation results, outperforming the previous state-of-the-art in both accuracy and speed. The combination of fast and accurate segmentation is not only beneficial for a posteriori data processing, it also makes online monitoring of thousands of trapped cells or closed-loop optimal experimental design feasible from an image processing perspective.

Publisher: IEEE
Uncontrolled Keywords: semantic segmentation, synthetic biology, biomedical image analysis, microfluidics, single-cell analysis, time-lapse fluorescent microscopy, deep learning
Divisions: 18 Department of Electrical Engineering and Information Technology
18 Department of Electrical Engineering and Information Technology > Institute for Telecommunications > Bioinspired Communication Systems
18 Department of Electrical Engineering and Information Technology > Institute for Telecommunications
Event Title: International Conference on Computational Intelligence in Bioinformatics and Computational Biology
Event Location: virtual Conference
Event Dates: October 27-29, 2020
Date Deposited: 22 Sep 2020 09:51
Official URL: https://www.bcs.tu-darmstadt.de/media/bcs/research_4/documen...
Related URLs:
Export:
Suche nach Titel in: TUfind oder in Google
Send an inquiry Send an inquiry

Options (only for editors)
Show editorial Details Show editorial Details