Check and Link: Pairwise Lesion Correspondence Guides Mammogram Mass Detection

TL;DR

This paper introduces CL-Net, a transformer-based framework that explicitly models pairwise lesion correspondence in mammogram mass detection, achieving state-of-the-art results and improved accuracy especially in low false positive scenarios.

Contribution

The paper proposes a novel end-to-end transformer framework with dynamic cross-view interaction and supervision-guided correspondence modeling for mammogram mass detection.

Findings

Achieves state-of-the-art performance on DDSM and in-house datasets.

Significantly outperforms previous methods in low FPI regimes.

Effectively models pairwise lesion correspondence with supervision.

Abstract

Detecting mass in mammogram is significant due to the high occurrence and mortality of breast cancer. In mammogram mass detection, modeling pairwise lesion correspondence explicitly is particularly important. However, most of the existing methods build relatively coarse correspondence and have not utilized correspondence supervision. In this paper, we propose a new transformer-based framework CL-Net to learn lesion detection and pairwise correspondence in an end-to-end manner. In CL-Net, View-Interactive Lesion Detector is proposed to achieve dynamic interaction across candidates of cross views, while Lesion Linker employs the correspondence supervision to guide the interaction process more accurately. The combination of these two designs accomplishes precise understanding of pairwise lesion correspondence for mammograms. Experiments show that CL-Net yields state-of-the-art performance on the public DDSM dataset and our in-house dataset. Moreover, it outperforms previous methods by a large margin in low FPI regime.