A-eye: Automated 3D MRI segmentation and morphometric feature extraction for eye and orbit atlas construction
Jaime Barranco, Adrian Konstantin Luyken, Yiwei Jia, Hamza Kebiri, Philipp Stachs, Pedro M Gordaliza, Oscar Esteban, Yasser Aleman · 2026
Read A-eye: Automated 3D MRI segmentation and morphometric feature extraction for eye and orbit atlas construction by Jaime Barranco, Adrian Konstantin Luyken, Yiwei Jia, Hamza Kebiri, Philipp Stachs, Pedro M Gordaliza, Oscar Esteban, Yasser Aleman (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/plos-pone-0352257.txt.
Description
Jaime Barranco and seven co-authors present this 2026 PLOS One imaging paper on the eye. It teaches a computer to outline the eye and its socket in MRI scans. Drawing these parts by hand is slow. That has kept eye-imaging studies small. The team used scans from more than twelve hundred adults. They trained a leading deep learning system to trace five parts: the lens, the eyeball, the optic nerve, the eye muscles, and the orbital fat.
The system traced all five parts well. It could also estimate eye length and tissue volumes on its own. That let the team check how eye parts relate to body mass at scale. As a headline product, they release the first large eye atlases made without bias. There are atlases for women, for men, and for both combined. They are meant to standardize future eye MRI research.
Catalog record
| CREATOR | Jaime Barranco, Adrian Konstantin Luyken, Yiwei Jia, Hamza Kebiri, Philipp Stachs, Pedro M Gordaliza, Oscar Esteban, Yasser Aleman |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 78023 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |