Perceived Realism of High-Resolution Generative Adversarial Network–derived Synthetic Mammograms

Dimitrios Korkinof, Hugh Harvey, Andreas Heindl, Edith Karpati, Gareth Williams, Tobias Rijken, Peter D. Kecskemethy, Ben GlockerRadiology 2020 · DOI

Abstract

On the basis of these findings, it appears possible to generate realistic synthetic full-field digital mammograms by using a progressive GAN architecture up to a resolution of 1280 × 1024 pixels.<i>Supplemental material is available for this article.</i>© RSNA, 2020.
BibTeX
@inproceedings{korkinof2020perceived,
  author = {Dimitrios Korkinof and Hugh Harvey and Andreas Heindl and Edith Karpati and Gareth Williams and Tobias Rijken and Peter D. Kecskemethy and Ben Glocker},
  title = {{Perceived Realism of High-Resolution Generative Adversarial Network–derived Synthetic Mammograms}},
  booktitle = {Radiology},
  year = {2020},
  doi = {10.1148/ryai.2020190181},
}

Loading related content...

Figure