VENturing into machine learning for the morphological analysis of von Economo neurons
Ivan Banovac, Oliver J Bruton, Luis Mercado-Díaz, Julian Tejada, Fernando Marmolejo-Ramos · 2025
Read VENturing into machine learning for the morphological analysis of von Economo neurons by Ivan Banovac, Oliver J Bruton, Luis Mercado-Díaz, Julian Tejada, Fernando Marmolejo-Ramos (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-12749959.txt.
Description
Ivan Banovac and co-authors train machine learners to tell rare von Economo neurons from ordinary pyramid cells by shape, in work from twenty twenty-five. These elongated neurons matter for higher thought and mental illness. Yet experts lack agreed, objective rules for spotting them. Hundreds of reconstructed neurons from a public database are classified. Six classic algorithms plus a neural network join the contest.
Accuracy runs high across the learning models overall. Dendrite length and stem count emerge as key discriminators. A heat-map method shows where the network looks when deciding. Expert labels agree only partly with the machines' verdicts. Experts even disagree noticeably among themselves in ratings. Most machine errors trace to flawed reconstructions, not the models. Dendrite shape may define these neurons as much as the body.
Catalog record
| CREATOR | Ivan Banovac, Oliver J Bruton, Luis Mercado-Díaz, Julian Tejada, Fernando Marmolejo-Ramos |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 69 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |