A deep learning-based toolkit for 3D nuclei segmentation and quantitative analysis in cellular and tissue context
Development · 2024
DOI: 10.1242/dev.202800 ↗At a glance
Journal article in Development, 2024. Written by Athul Vijayan and 10 co-authors. Institution: Plant Developmental Biology, TUM School of Life Sciences, Technical University of Munich, Freising 85354, Germany. Major MEDLINE topics: Deep Learning, Cell Nucleus, Imaging, Three-Dimensional, Software. Cited 23 times so far (Crossref); 64 references. The full text is freely available (open access, CC BY 4.0). Funded by: Deutsche Forschungsgemeinschaft, Technische Universität München.
Abstract (original language)
We present a new set of computational tools that enable accurate and widely applicable 3D segmentation of nuclei in various 3D digital organs. We have developed an approach for ground truth generation and iterative training of 3D nuclear segmentation models, which we applied to popular CellPose, PlantSeg and StarDist algorithms. We provide two high-quality models trained on plant nuclei that enable 3D segmentation of nuclei in datasets obtained from fixed or live samples, acquired from different plant and animal tissues, and stained with various nuclear stains or fluorescent protein-based nuclear reporters. We also share a diverse high-quality training dataset of about 10,000 nuclei. Furthermore, we advanced the MorphoGraphX analysis and visualization software by, among other things, providing a method for linking 3D segmented nuclei to their surrounding cells in 3D digital organs. We found that the nuclear-to-cell volume ratio varies between different ovule tissues and during the development of a tissue. Finally, we extended the PlantSeg 3D segmentation pipeline with a proofreading tool that uses 3D segmented nuclei as seeds to correct cell segmentation errors in difficult-to-segment tissues.
Subjects
MeSH terms (MEDLINE)
Author keywords
Authors and institutions
- Plant Developmental Biology, TUM School of Life Sciences, Technical University of Munich, Freising 85354, Germany.
- European Molecular Biology Laboratory, Heidelberg 69117, Germany.
- Collaboration for joint PhD degree between European Molecular Biology Laboratory and Heidelberg University, Faculty of Biosciences, Heidelberg 69117, Germany.
- Interdsisciplinary Center for Scientific Computing (IWR), Heidelberg University, Heidelberg 69120, Germany.
- Department of Comparative Developmental and Genetics, Max Planck Institute for Plant Breeding Research, Cologne 50829, Germany.
- Computational and Systems Biology, The John Innes Centre, Norwich Research Park, Norwich NR4 7UH, UK.
ORCID profiles: Athul Vijayan, Tejasvinee Atul Mody, Qin Yu, Adrian Wolny, Lorenzo Cerrone, Soeren Strauss, Miltos Tsiantis, Richard S Smith, Anna Kreshuk, Kay Schneitz
Funding
- Deutsche Forschungsgemeinschaft
- Technische Universität München
Cite
APA
Vijayan, A., Mody, T. A., Yu, Q., Wolny, A., Cerrone, L., Strauss, S., Tsiantis, M., Smith, R. S., Hamprecht, F. A., Kreshuk, A., & Schneitz, K. (2024). A deep learning-based toolkit for 3D nuclei segmentation and quantitative analysis in cellular and tissue context. Development. https://doi.org/10.1242/dev.202800
Vancouver
Vijayan A, Mody TA, Yu Q, Wolny A, Cerrone L, Strauss S, et al. A deep learning-based toolkit for 3D nuclei segmentation and quantitative analysis in cellular and tissue context. Development. 2024. doi:10.1242/dev.202800
BibTeX
@article{Vijayan2024,
author = {Vijayan, Athul and Mody, Tejasvinee Atul and Yu, Qin and Wolny, Adrian and Cerrone, Lorenzo and Strauss, Soeren and Tsiantis, Miltos and Smith, Richard S and Hamprecht, Fred A and Kreshuk, Anna and Schneitz, Kay},
title = {A deep learning-based toolkit for 3D nuclei segmentation and quantitative analysis in cellular and tissue context},
journal = {Development},
year = {2024},
doi = {10.1242/dev.202800}
}
EUVIMED