Visualizing chest X-ray dataset biases using GANs
This work addresses fairness issues in medical imaging for healthcare applications, but it is incremental as it builds on prior findings about biases in chest X-ray datasets.
The authors tackled the problem of visualizing dataset biases in chest X-ray images by using GANs to identify features that differ between demographic subgroups, aiming to address fairness concerns in clinical predictions.
Recent work demonstrates that images from various chest X-ray datasets contain visual features that are strongly correlated with protected demographic attributes like race and gender. This finding raises issues of fairness, since some of these factors may be used by downstream algorithms for clinical predictions. In this work, we propose a framework, using generative adversarial networks (GANs), to visualize what features are most different between X-rays belonging to two demographic subgroups.