A Single-organoid Workflow for quantitative Imaging classiFication and Tracking (SWIFT)
SWIFT (Single-organoid Workflow for quantitative Imaging classiFication and Tracking) is a fast and modular pipeline for quantitative, time-resolved organoid analysis from brightfield images. Requiring only minimal training annotations, SWIFT combines YOLOv8, SAM, and application-specific object classification to deliver accurate single-organoid segmentation, phenotyping, and tracking. The workflow is robust across organoid types and microscope systems. Applied to intestinal organoids, SWIFT uncovers dynamic Wnt-dependent morphological transitions, enabling scalable, high-throughput studies of epithelial plasticity.
Authors
- Béatrice Kunz
- Lucie Bracq (ORCID: https://orcid.org/0000-0001-5909-7984)
- Romain Guiet (ORCID: https://orcid.org/0000-0001-6715-4897)
- Nathalie Brandenberg (ORCID: https://orcid.org/0000-0002-1609-1862)
- Gijs R. van den Brink (ORCID: https://orcid.org/0000-0002-8522-274X)
- Sandra Offner
Institutions
- École Polytechnique Fédérale de Lausanne (CH)
Publication Details
- Journal
- Communications Biology
- Published
- 2026-09-01
- DOI
- https://doi.org/10.1038/s42003-026-10768-x
- Primary Topic
- Cancer Cells and Metastasis
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Science Foundation
- École Polytechnique Fédérale de Lausanne
- Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung