Fairness Evolution in Continual Learning for Medical Imaging

TL;DR

This paper investigates how fairness biases evolve in continual learning models for medical imaging, highlighting that some strategies maintain better fairness while achieving high classification accuracy.

Contribution

It introduces an analysis of bias evolution in continual learning for medical imaging and compares strategies based on fairness metrics alongside performance.

Findings

Learning without Forgetting and Pseudo-Label achieve high accuracy

Pseudo-Label exhibits less bias than other strategies

Bias evolution varies across different CL methods

Abstract

Deep Learning has advanced significantly in medical applications, aiding disease diagnosis in Chest X-ray images. However, expanding model capabilities with new data remains a challenge, which Continual Learning (CL) aims to address. Previous studies have evaluated CL strategies based on classification performance; however, in sensitive domains such as healthcare, it is crucial to assess performance across socially salient groups to detect potential biases. This study examines how bias evolves across tasks using domain-specific fairness metrics and how different CL strategies impact this evolution. Our results show that Learning without Forgetting and Pseudo-Label achieve optimal classification performance, but Pseudo-Label is less biased.