Features Fusion for Dual-View Mammography Mass Detection

TL;DR

This paper introduces MAMM-Net, a dual-view mammography detection model that fuses information at multiple levels using deformable attention, achieving superior accuracy and providing detailed lesion annotations.

Contribution

The paper presents a novel dual-view mammography detection model with feature-level fusion and deformable attention, enhancing detection accuracy and lesion classification.

Findings

Outperforms previous state-of-the-art on DDSM dataset

Provides pixel-level lesion annotations

Classifies lesion malignancy effectively

Abstract

Detection of malignant lesions on mammography images is extremely important for early breast cancer diagnosis. In clinical practice, images are acquired from two different angles, and radiologists can fully utilize information from both views, simultaneously locating the same lesion. However, for automatic detection approaches such information fusion remains a challenge. In this paper, we propose a new model called MAMM-Net, which allows the processing of both mammography views simultaneously by sharing information not only on an object level, as seen in existing works, but also on a feature level. MAMM-Net's key component is the Fusion Layer, based on deformable attention and designed to increase detection precision while keeping high recall. Our experiments show superior performance on the public DDSM dataset compared to the previous state-of-the-art model, while introducing new helpful features such as lesion annotation on pixel-level and classification of lesions malignancy.