Generalized Robust Fundus Photography-based Vision Loss Estimation for High Myopia

TL;DR

This paper introduces a novel, efficient framework that improves the accuracy and robustness of vision loss estimation from fundus photographs in high myopia patients, especially across diverse populations and data sources.

Contribution

The paper proposes a parameter-efficient RED module that enhances generalization of VF estimation models across different datasets and populations.

Findings

Significantly outperforms existing methods in RMSE, MAE, and correlation coefficient.

Effective in both in-distribution and out-of-distribution data validation.

Offers practical clinical utility for ophthalmic practices.

Abstract

High myopia significantly increases the risk of irreversible vision loss. Traditional perimetry-based visual field (VF) assessment provides systematic quantification of visual loss but it is subjective and time-consuming. Consequently, machine learning models utilizing fundus photographs to estimate VF have emerged as promising alternatives. However, due to the high variability and the limited availability of VF data, existing VF estimation models fail to generalize well, particularly when facing out-of-distribution data across diverse centers and populations. To tackle this challenge, we propose a novel, parameter-efficient framework to enhance the generalized robustness of VF estimation on both in- and out-of-distribution data. Specifically, we design a Refinement-by-Denoising (RED) module for feature refinement and adaptation from pretrained vision models, aiming to learn high-entropy feature representations and to mitigate the domain gap effectively and efficiently. Through independent validation on two distinct real-world datasets from separate centers, our method significantly outperforms existing approaches in RMSE, MAE and correlation coefficient for both internal and external validation. Our proposed framework benefits both in- and out-of-distribution VF estimation, offering significant clinical implications and potential utility in real-world ophthalmic practices.