Conference Proceedings: International Conference on Medical Imaging with Deep Learning (MIDL) 2019
Publishing Date: 17th April 2019
Pre-print here: 9th July 2018
We explore whether recent advances in generative adversarial networks (GANs) enable synthesis of realistic medical images that are hard to distinguish from real ones, even by domain experts. High-quality synthetic images can be useful for data augmentation, domain transfer, and out-of-distribution detection. However, generating realistic images is challenging, particularly for Full Field Digital Mammograms (FFDM), due to the high resolution, textural heterogeneity, fine structural details and specific tissue properties. We employ progressive GANs to synthesize mammograms at a resolution of 1280x1024 pixels, the highest reported so far. In order to assess the perceptual realism, we designed a user study where experts are asked to distinguish real and generated images with exciting results.