Fig. 11
From: Improving lesion detection in mammograms by leveraging a Cycle-GAN-based lesion remover
True negative normal controls that changed to false positive after applying the lesion highlighter. This figure shows two normal controls which were true negative before applying the lesion highlighter but changed to false positive after applying the lesion remover. The first and third column show the images with normal tissue with (top row) and without (bottom row) applying the lesion highlighter. The second and last column show the attention map by the detector. We found that our method falsely identified the normal breast tissue as lesions such that it was falsely highlighted in green, which made the lesion detector identify it as a lesion