High-resolution synthesis of high-density breast mammograms: Application to improved fairness in deep learning based mass detection

TL;DR

This paper introduces a novel data augmentation method using high-resolution synthetic mammograms generated by CycleGANs to enhance deep learning-based breast mass detection, especially in dense breasts, improving sensitivity and generalization.

Contribution

The study develops a high-resolution synthetic mammogram generation technique to augment training data, improving detection performance and fairness across breast densities.

Findings

Synthetic data improved detection sensitivity in small datasets.

Enhanced model generalization across different datasets.

Clinical realism of synthetic images validated by expert radiologists.

Abstract

Computer-aided detection systems based on deep learning have shown good performance in breast cancer detection. However, high-density breasts show poorer detection performance since dense tissues can mask or even simulate masses. Therefore, the sensitivity of mammography for breast cancer detection can be reduced by more than 20% in dense breasts. Additionally, extremely dense cases reported an increased risk of cancer compared to low-density breasts. This study aims to improve the mass detection performance in highdensity breasts using synthetic high-density full-field digital mammograms (FFDM) as data augmentation during breast mass detection model training. To this end, a total of five cycle-consistent GAN (CycleGAN) models using three FFDM datasets were trained for low-to-high-density image translation in highresolution mammograms. The training images were split by breast density BIRADS categories, being BI-RADS A almost entirely fatty and BI-RADS D extremely dense breasts. Our results showed that the proposed data augmentation technique improved the sensitivity and precision of mass detection in models trained with small datasets and improved the domain generalization of the models trained with large databases. In addition, the clinical realism of the synthetic images was evaluated in a reader study involving two expert radiologists and one surgical oncologist.