Impact of GAN artifacts for simulating mammograms on identifying mammographically occult cancer.
Juhun LeeTamerlan MustafaevRobert M NishikawaPublished in: Journal of medical imaging (Bellingham, Wash.) (2023)
We found that artifacts were pervasive in the CGAN-simulated mammograms. However, they did not negatively affect our MO cancer detection algorithm; the simulated mammograms still provided complementary information for MO cancer detection when combined with real mammograms.