Visualizing chest X-ray dataset biases using GANsDownload PDF

Published: 28 Apr 2023, Last Modified: 15 Jun 2023MIDL 2023 Short paper track PosterReaders: Everyone
Keywords: Chest X-rays, fairness, bias, explainability, generative adversarial networks (GANs)
Abstract: 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.
2 Replies