Synthesis of large scale 3D microscopic images of 3D cell cultures for training and benchmarking
PLOS ONE · 2023
DOI: 10.1371/journal.pone.0283828 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS ONE, 2023. Verfasst von Roman Bruch und 6 weiteren Autor:innen. Beteiligte Einrichtung: Institute for Automation and Applied Informatics, Karlsruhe Institute of Technology, Eggenstein-Leopoldshafen, Germany. Hauptthemen laut MEDLINE: Deep Learning. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Bundesministerium für Bildung und Forschung, Carl-Zeiss-Stiftung.
Abstract (Originalsprache)
The analysis of 3D microscopic cell culture images plays a vital role in the development of new therapeutics. While 3D cell cultures offer a greater similarity to the human organism than adherent cell cultures, they introduce new challenges for automatic evaluation, like increased heterogeneity. Deep learning algorithms are able to outperform conventional analysis methods in such conditions but require a large amount of training data. Due to data size and complexity, the manual annotation of 3D images to generate large datasets is a nearly impossible task. We therefore propose a pipeline that combines conventional simulation methods with deep-learning-based optimization to generate large 3D synthetic images of 3D cell cultures where the labels are known by design. The hybrid procedure helps to keep the generated image structures consistent with the underlying labels. A new approach and an additional measure are introduced to model and evaluate the reduced brightness and quality in deeper image regions. Our analyses show that the deep learning optimization step consistently improves the quality of the generated images. We could also demonstrate that a deep learning segmentation model trained with our synthetic data outperforms a classical segmentation method on real image data. The presented synthesis method allows selecting a segmentation model most suitable for the user’s data, providing an ideal basis for further data analysis.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Institute for Automation and Applied Informatics, Karlsruhe Institute of Technology, Eggenstein-Leopoldshafen, Germany.
- Institute of Molecular and Cell Biology, Mannheim University of Applied Sciences, Mannheim, Germany.
ORCID-Profile: Roman Bruch, Moritz Böhland
Förderung
- Bundesministerium für Bildung und Forschung
- Carl-Zeiss-Stiftung
Zitieren
APA
Bruch, R., Keller, F., Böhland, M., Vitacolonna, M., Klinger, L., Rudolf, R., & Reischl, M. (2023). Synthesis of large scale 3D microscopic images of 3D cell cultures for training and benchmarking. PLOS ONE. https://doi.org/10.1371/journal.pone.0283828
Vancouver
Bruch R, Keller F, Böhland M, Vitacolonna M, Klinger L, Rudolf R, et al. Synthesis of large scale 3D microscopic images of 3D cell cultures for training and benchmarking. PLOS ONE. 2023. doi:10.1371/journal.pone.0283828
BibTeX
@article{Bruch2023,
author = {Bruch, Roman and Keller, Florian and Böhland, Moritz and Vitacolonna, Mario and Klinger, Lukas and Rudolf, Rüdiger and Reischl, Markus},
title = {Synthesis of large scale 3D microscopic images of 3D cell cultures for training and benchmarking},
journal = {PLOS ONE},
year = {2023},
doi = {10.1371/journal.pone.0283828}
}
EUVIMED