Deep-learning deconvolution and segmentation of fluorescent membranes for high-precision bacterial cell-size profiling
Octavio Reyes-Matte, Carsten Fortmann-Grote, Beate Gericke, Nadja Hüttmann, Nikola Ojkic, Javier López-Garrido · 2026
Read Deep-learning deconvolution and segmentation of fluorescent membranes for high-precision bacterial cell-size profiling by Octavio Reyes-Matte, Carsten Fortmann-Grote, Beate Gericke, Nadja Hüttmann, Nikola Ojkic, Javier López-Garrido (2026) 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-13194920.txt.
Description
Octavio Reyes-Matte is first author on a 2026 methods paper on measuring bacterial cell size precisely at scale. Bacteria vary hugely in size, and size can evolve quickly, yet comparative size studies are rare because manual measurement is slow and standard imaging segments cells poorly. The team built a pipeline named MEDUSSA.
Deep learning first sharpens fluorescent membrane images, then segments individual cells, corrects errors, and measures each one regardless of shape, chaining, or clustering. Applied to six strains of one bacterial species, the method found over twofold volume differences, driven mainly by cell width. A partly working gene variant explained one strain's narrowness. The toolkit opens comparative study of how bacterial size evolves.
Catalog record
| CREATOR | Octavio Reyes-Matte, Carsten Fortmann-Grote, Beate Gericke, Nadja Hüttmann, Nikola Ojkic, Javier López-Garrido |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 70 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |