Classification and Detection in Mammograms with Weak Supervision via Dual Branch Deep Neural Net

TL;DR

This paper introduces a dual-branch deep neural network for mammogram classification and localization using weak supervision, reducing the need for detailed annotations while accurately identifying and localizing anomalies.

Contribution

The study presents a novel dual-branch architecture that combines region classification and ranking for weakly supervised mammogram analysis, improving localization and classification performance.

Findings

Outperforms previous weakly-supervised methods

Effective localization of anomalies in full resolution

Validated on a large multi-center dataset

Abstract

The high cost of generating expert annotations, poses a strong limitation for supervised machine learning methods in medical imaging. Weakly supervised methods may provide a solution to this tangle. In this study, we propose a novel deep learning architecture for multi-class classification of mammograms according to the severity of their containing anomalies, having only a global tag over the image. The suggested scheme further allows localization of the different types of findings in full resolution. The new scheme contains a dual branch network that combines region-level classification with region ranking. We evaluate our method on a large multi-center mammography dataset including $\sim$3,000 mammograms with various anomalies and demonstrate the advantages of the proposed method over a previous weakly-supervised strategy.