A training regime to learn unified representations from complementary breast imaging modalities

TL;DR

This paper introduces a machine learning approach that learns unified representations from both FFDM and DBT breast imaging modalities, improving lesion detection accuracy and potentially reducing exam times and radiation exposure.

Contribution

A novel training regime that combines FFDM and DBT data to learn high-level, unified representations for enhanced breast cancer detection.

Findings

Unified representations outperform single-modality models in lesion detection

The approach reduces reliance on FFDM, potentially lowering radiation dose

Large-scale experiments validate improved diagnostic accuracy

Abstract

Full Field Digital Mammograms (FFDMs) and Digital Breast Tomosynthesis (DBT) are the two most widely used imaging modalities for breast cancer screening. Although DBT has increased cancer detection compared to FFDM, its widespread adoption in clinical practice has been slowed by increased interpretation times and a perceived decrease in the conspicuity of specific lesion types. Specifically, the non-inferiority of DBT for microcalcifications remains under debate. Due to concerns about the decrease in visual acuity, combined DBT-FFDM acquisitions remain popular, leading to overall increased exam times and radiation dosage. Enabling DBT to provide diagnostic information present in both FFDM and DBT would reduce reliance on FFDM, resulting in a reduction in both quantities. We propose a machine learning methodology that learns high-level representations leveraging the complementary diagnostic signal from both DBT and FFDM. Experiments on a large-scale data set validate our claims and show that our representations enable more accurate breast lesion detection than any DBT- or FFDM-based model.