Segment Anything for Microscopy 2
Foundation models have advanced microscopy image segmentation, but existing models are trained on two-dimensional data, struggle with complex structures in volumetric data, and address only a narrow range of analysis tasks. Here we present Segment Anything for Microscopy 2 (μSAM2), a foundation model that adapts SAM2 to joint 2D and 3D segmentation in light and electron microscopy. Trained on annotations of more than 23 million cells and nuclei and 1.6 million cellular structures, μSAM2 achieves state-of-the-art automatic and interactive segmentation and outperforms generalist and specialist methods on volumetric data. Dedicated models further enable accurate mitochondrion and nucleus segmentation in electron microscopy. Beyond segmentation, μSAM2 supports pixel and object classification from few annotations as well as cell tracking in 2D and 3D time-lapse data. All functionality is available in the user-friendly μSAM napari plugin. We demonstrated the capabilities of μSAM2 on challenging use cases spanning developmental biology, organoid research, cardiac physiology, and histopathology.
Authors
- Mostafa Aakhte (ORCID: https://orcid.org/0000-0003-4685-5576)
- Mette Handberg-Thorsager (ORCID: https://orcid.org/0000-0002-3908-7233)
- Jan Huisken (ORCID: https://orcid.org/0000-0001-7250-3756)
- Constantin Pape (ORCID: https://orcid.org/0000-0001-6562-7187)
- Dominic Gruen
- Anne Béghin (ORCID: https://orcid.org/0000-0002-7231-6245)
- Isabelle Bonne (ORCID: https://orcid.org/0000-0002-8261-6794)
- Nadine Vornberger
- Anwai Archit (ORCID: https://orcid.org/0009-0002-9533-8620)
- Lisa Marschhäuser
- Carolin Teuber (ORCID: https://orcid.org/0009-0004-3866-191X)
- Sebastian von Haaren
- Beke Lohmann (ORCID: https://orcid.org/0009-0006-0076-0159)
- Titus Griebel
Institutions
- National University of Singapore (SG)
- University of Würzburg (DE)
- UNSW Sydney (AU)
- Universitätsmedizin Göttingen (DE)
- Max Planck Institute for Multidisciplinary Sciences (DE)
- CAIMed - Niedersächsisches Zentrum für KI und Kausale Methoden in der Medizin (DE)
- University of Göttingen (DE)
Publication Details
- Journal
- bioRxiv (Cold Spring Harbor Laboratory)
- Published
- 2026-11-17
- DOI
- https://doi.org/10.64898/2026.11.12.766082
- Primary Topic
- Cell Image Analysis Techniques
- Type
- preprint