Self-adversarial Learning for Detection of Clustered Microcalcifications in Mammograms

Microcalcification (MC) clusters in mammograms are one of the primary signs of breast cancer. In the literature, most MC detection methods follow a two-step paradigm: segmenting each MC and analyzing their spatial distributions to form MC clusters. However, segmentation of MCs cannot avoid low sensitivity or high false positive rate due to their variability in size (sometimes <0.1 mm), brightness, and shape (with diverse surroundings). In this paper, we propose a novel self-adversarial learning framework to differentiate and delineate the MC clusters in an end-to-end manner. The class activation mapping (CAM) mechanism is employed to directly generate the contours of MC clusters with the guidance of MC cluster classification and box annotations. We also propose the self-adversarial learning strategy to equip CAM with better detection capability of MC clusters by using the backbone network itself as a discriminator. Experimental results suggest that our method can achieve better performance for MC cluster detection with the contouring of MC clusters and classification of MC types.