Back

A-eye: Automated 3D Segmentation of Healthy Human Eyeand Orbit Structures and Axial Length Extraction

Barranco, J.; Luyken, A. K.; Stachs, O.; Langner, S.; Franceschiello, B.; Bach Cuadra, M.

2025-05-09 bioengineering
10.1101/2025.05.05.652187 bioRxiv
Show abstract

This study addresses the need for accurate 3D segmentation of the human eye and orbit from MRI to improve ophthalmic diagnostics. Past efforts focused on small sample sizes and varied imaging methods. Here, two techniques (atlas-based registration and supervised deep learning) are tested for automated segmentation on a large T1-weighted MRI dataset. Results show accurate segmentations of the lens, globe, optic nerve, rectus muscles, and fat. Additionally, the study automates the estimation of axial length, a key biomarker.

Matching journals

The top 7 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.