BasNet: Attention U-Net-Based Automated Axon Segmentation in Bielschowsky Silver-Stained Histology
Lukas Schönenberger, Laurin Egli, Dimitrios Gkotsoulias, Christine Stadelmann, Cristina Granziera · 2026
Read BasNet: Attention U-Net-Based Automated Axon Segmentation in Bielschowsky Silver-Stained Histology by Lukas Schönenberger, Laurin Egli, Dimitrios Gkotsoulias, Christine Stadelmann, Cristina Granziera (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-13553709.txt.
Description
Counting nerve fibers in stained brain slices by hand is slow work, and two raters can disagree. Lukas Schönenberger and four co-authors built BasNet in 2026, a tool that does the count on its own for slices dyed with the Bielschowsky silver stain. Old color-based ways do poorly on silver stains, so the team turned to an attention U-Net, a net that learns where to look as it marks each pixel.
Hand-marked truth came from thirty-three tiles cut from slides of four folk with multiple sclerosis. On held-out tiles the tool scored in line with, or above, the match between two human raters. Whole-slide maps of fiber counts and fiber paths came out true to the real spread. The open tool aims to cut hand work and give steady counts for studies of nerve harm.
Catalog record
| CREATOR | Lukas Schönenberger, Laurin Egli, Dimitrios Gkotsoulias, Christine Stadelmann, Cristina Granziera |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 50 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |