Operator learning for models of tear film breakup

TL;DR

This paper introduces a neural operator framework to efficiently analyze tear film breakup from fluorescence imaging, replacing traditional inverse problem solvers with a scalable, data-driven method for studying dry eye disease.

Contribution

It presents a novel neural operator approach trained on simulated tear film dynamics to rapidly estimate tear film properties from imaging data.

Findings

Achieves faster analysis compared to traditional methods

Demonstrates accurate estimation of tear film parameters

Provides a scalable solution for tear film dynamics modeling

Abstract

Tear film (TF) breakup is a key driver of understanding dry eye disease, yet estimating TF thickness and osmolarity from fluorescence (FL) imaging typically requires solving computationally expensive inverse problems. We propose an operator learning framework that replaces traditional inverse solvers with neural operators trained on simulated TF dynamics. This approach offers a scalable path toward rapid, data-driven analysis of tear film dynamics.