Harvard Glaucoma Fairness: A Retinal Nerve Disease Dataset for Fairness Learning and Fair Identity Normalization

TL;DR

This paper introduces Harvard-GF, a balanced retinal imaging dataset for glaucoma detection across racial groups, and proposes a fairness normalization method to improve equitable performance in medical imaging models.

Contribution

The paper provides the first public retinal dataset with balanced racial groups for fairness learning and introduces a novel fairness normalization technique for medical imaging.

Findings

FIN outperforms existing fairness methods in racial, gender, and ethnicity fairness tasks.

Harvard-GF enables fairer glaucoma detection across diverse racial groups.

The equity-scaled performance measure facilitates comprehensive fairness evaluation.

Abstract

Fairness (also known as equity interchangeably) in machine learning is important for societal well-being, but limited public datasets hinder its progress. Currently, no dedicated public medical datasets with imaging data for fairness learning are available, though minority groups suffer from more health issues. To address this gap, we introduce Harvard Glaucoma Fairness (Harvard-GF), a retinal nerve disease dataset with both 2D and 3D imaging data and balanced racial groups for glaucoma detection. Glaucoma is the leading cause of irreversible blindness globally with Blacks having doubled glaucoma prevalence than other races. We also propose a fair identity normalization (FIN) approach to equalize the feature importance between different identity groups. Our FIN approach is compared with various the-state-of-the-art fairness learning methods with superior performance in the racial, gender, and ethnicity fairness tasks with 2D and 3D imaging data, which demonstrate the utilities of our dataset Harvard-GF for fairness learning. To facilitate fairness comparisons between different models, we propose an equity-scaled performance measure, which can be flexibly used to compare all kinds of performance metrics in the context of fairness. The dataset and code are publicly accessible via \url{https://ophai.hms.harvard.edu/datasets/harvard-glaucoma-fairness-3300-samples/}.