EmbSAM: cell boundary localization and Segment Anything Model for fast images of developing embryos
Guoye Guan, Cunmin Zhao, Zelin Li, Pei Zhang, Yixuan Chen, Pohao Ye, Ming-Kin Wong, Lu-Yan Chan, Hong Yan, Chao Tang, Zhongying Zhao · 2025
Read EmbSAM: cell boundary localization and Segment Anything Model for fast images of developing embryos by Guoye Guan, Cunmin Zhao, Zelin Li, Pei Zhang, Yixuan Chen, Pohao Ye, Ming-Kin Wong, Lu-Yan Chan, Hong Yan, Chao Tang, Zhongying Zhao (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12764838.txt.
Description
Guoye Guan and co-authors built a tool that traces cell shapes in fast movies of growing worm embryos. Watching cells divide and shift shows how fate and body form arise. Yet live images of cell membranes are faint, since strong light harms the embryo and bleaches the dye, and the noise hides cell borders.
Their framework, EmbSAM, pairs a deep learning step that locates cell boundaries with the Segment Anything Model. It segments three-dimensional membrane images of Caenorhabditis elegans embryos taken every ten seconds. The traced shapes let the team measure how division timing, axis turns, position, and lineage link to cell fate before gastrulation. Results can be explored both locally and online.
Catalog record
| CREATOR | Guoye Guan, Cunmin Zhao, Zelin Li, Pei Zhang, Yixuan Chen, Pohao Ye, Ming-Kin Wong, Lu-Yan Chan, Hong Yan, Chao Tang, Zhongying Zhao |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 134 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |