Assessing the ability of generative adversarial networks to learn canonical medical image statistics
This work addresses the reliability of GANs for medical imaging applications by highlighting gaps in learning objective quality measures, which is crucial for ensuring accurate downstream tasks in healthcare.
The study evaluated whether a state-of-the-art GAN could learn canonical medical image statistics relevant for objective quality assessment, finding it successfully learned basic first- and second-order statistics but failed to capture several per-image statistics, despite generating high perceptual quality images.
In recent years, generative adversarial networks (GANs) have gained tremendous popularity for potential applications in medical imaging, such as medical image synthesis, restoration, reconstruction, translation, as well as objective image quality assessment. Despite the impressive progress in generating high-resolution, perceptually realistic images, it is not clear if modern GANs reliably learn the statistics that are meaningful to a downstream medical imaging application. In this work, the ability of a state-of-the-art GAN to learn the statistics of canonical stochastic image models (SIMs) that are relevant to objective assessment of image quality is investigated. It is shown that although the employed GAN successfully learned several basic first- and second-order statistics of the specific medical SIMs under consideration and generated images with high perceptual quality, it failed to correctly learn several per-image statistics pertinent to the these SIMs, highlighting the urgent need to assess medical image GANs in terms of objective measures of image quality.