Towards an Unbiased Classification of Chest X-ray Images Using a RL Powered ACGAN Framework

Computer-aided diagnosis systems are invaluable tools for healthcare providers given the overwhelming volume of medical data at their disposal. However, a significant challenge of these systems is the existence of bias in their diagnostic outcomes, particularly affecting certain protected groups who are more susceptible to receiving incorrect diagnoses. In this paper, we investigate bias mitigation strategies, leveraging the discriminator of auxiliary conditional generative adversarial networks as well as reinforcement learning agents for the classification of chest X-ray images. Our research targets bias reduction by deploying reward functions designed to enhance the true positivity rate of the discriminator. We explore the impact of a hierarchical label distribution-based reward, a novel approach that aims to further improve bias in the diagnostic process. Through extensive evaluation and comparison, we study the disparities in true positivity rates across various different approaches. We also highlight the efficiency of each strategy in achieving more equitable diagnostic outcomes.