Common cellular segmentation models based on machine learning perform suboptimally for test images that differ greatly from training images. Cellpose 2.0 allows biologists to quickly train state-of-the-art segmentation models on their own imaging data. This was previously only possible using large, annotated datasets and required expert machine learning knowledge.
This is a preview of subscription content, access via your institution
Access options
Access Nature and 54 other Nature Portfolio journals
Get Nature+, our best-value online-access subscription
$29.99 / 30 days
cancel any time
Subscribe to this journal
Receive 12 print issues and online access
$259.00 per year
only $21.58 per issue
Buy this article
- Purchase on Springer Link
- Instant access to full article PDF
Prices may be subject to local taxes which are calculated during checkout
References
Boutros, M., Heigwer, F. & Laufer, C. Microscopy-based high-content screening. Cell 163, 1314–1325 (2015). A Review article that presents various image-based screening methods and the image analysis techniques required to interpret the data.
Caicedo, J. C. et al. Nucleus segmentation across imaging experiments: the 2018 Data Science Bowl. Nat. Methods 16, 1247–1253 (2019). This paper reports the results of the Data Science Bowl nuclear segmentation challenge, in which models trained on the most comprehensive image set performed best.
Stringer, C., Wang, T., Michaelos, M. & Pachitariu, M. Cellpose: a generalist algorithm for cellular segmentation. Nat. Methods 18, 100–106 (2021). This paper introduces the original Cellpose segmentation model and cellular dataset.
Greenwald, N. F. et al. Whole-cell segmentation of tissue images with human-level performance using large-scale data annotation and deep learning. Nat. Biotechnol. 40, 555–565 (2021). This paper introduces the Mesmer segmentation model and the TissueNet dataset, which contains over 1 million manually labeled cells from different tissues and fluorescent imaging platforms.
Edlund, C. et al. LiveCell—a large-scale dataset for label-free live cell segmentation. Nat. Methods 18, 1038–1045 (2021). This paper introduces the LiveCell dataset, which contains over 1.6 million manually labeled cells in phase contrast images from various cell culture lines.
Additional information
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
This is a summary of: Pachitariu, M. & Stringer, C. Cellpose 2.0: how to train your own model. Nat. Methods https://doi.org/10.1038/s41592-022-01663-4 (2022).
Rights and permissions
About this article
Cite this article
A cellular segmentation algorithm with fast customization. Nat Methods 19, 1536–1537 (2022). https://doi.org/10.1038/s41592-022-01664-3
Published:
Issue Date:
DOI: https://doi.org/10.1038/s41592-022-01664-3
