Super-resolution multi-contrast unbiased eye atlases with deep probabilistic refinement

arXiv:2401.03060v2 Announce Type: replace-cross
Abstract: Purpose: Eye morphology varies significantly across the population, especially for the orbit and optic nerve. These variations limit the feasibility and robustness of generalizing population-wise features of eye organs to an unbiased spatial reference.
Approach: To tackle these limitations, we propose a process for creating high-resolution unbiased eye atlases. First, to restore spatial details from scans with a low through-plane resolution compared to a high in-plane resolution, we apply a deep learning-based super-resolution algorithm. Then, …

abstract arxiv contrast cs.cv eess.iv features limitations optic population process reference replace resolution robustness spatial type unbiased wise