Fig. 1From: Deep learning networks find unique mammographic differences in previous negative mammograms between interval and screen-detected cancers: a case-case studySchematic of the architecture of the deep learning network used in this study. YxY conv, M/N = M kernels of YxYx3 size and stride length of N (N = 1 if only M is listed). Fully Connected (FC) Layer = Dense (256), Dropout, Dense (1)Back to article page