Act Like a Radiologist: Towards Reliable Multi-view Correspondence Reasoning for Mammogram Mass Detection.

Mammogram mass detection is crucial for diagnosing and preventing breast cancers in clinical practice. The complementary effect of multi-view mammogram images provides valuable information about the breast anatomical prior structure and is of great significance in digital mammography interpretation. However, unlike radiologists who can utilize reasoning ability to identify masses, how to endow existing models with capability of multi-view reasoning is vital in clinical diagnosis. In this paper, we propose an Anatomy-aware Graph convolutional Network (AGN), which is tailored for mammogram mass detection and endows existing methods with multi-view reasoning ability. The proposed AGN consists of three steps. Firstly, we introduce a Bipartite Graph convolutional Network (BGN) to model intrinsic geometric and semantic relations of ipsilateral views. Secondly, considering that visual asymmetry of bilateral views is widely adopted in clinical practice to assist the diagnosis of breast lesions, we propose an Inception Graph convolutional Network (IGN) to model structural similarities of bilateral views. Finally, based on the constructed graphs, the multi-view information is propagated through nodes methodically, which equips the learned features with multi-view reasoning ability. Experiments on two benchmarks reveal that AGN significantly exceeds the state-of-the-art performance. Visualization results show that AGN provides interpretable visual cues for clinical diagnosis.