High-Resolution Mammogram Synthesis using Progressive Generative Adversarial Networks

TL;DR

This paper demonstrates the first successful generation of high-resolution (1280x1024) synthetic mammograms using progressive GANs, addressing challenges in medical image realism and resolution.

Contribution

It introduces a progressive training approach for GANs that produces realistic high-resolution mammograms, surpassing previous resolution limits in medical image synthesis.

Findings

Achieved up to 1280x1024 resolution in synthetic mammograms

Demonstrated realistic texture and structural details in generated images

Facilitated visualizations compatible with standard mammographic protocols

Abstract

The ability to generate synthetic medical images is useful for data augmentation, domain transfer, and out-of-distribution detection. However, generating realistic, high-resolution medical images is challenging, particularly for Full Field Digital Mammograms (FFDM), due to the textural heterogeneity, fine structural details and specific tissue properties. In this paper, we explore the use of progressively trained generative adversarial networks (GANs) to synthesize mammograms, overcoming the underlying instabilities when training such adversarial models. This work is the first to show that generation of realistic synthetic medical images is feasible at up to 1280x1024 pixels, the highest resolution achieved for medical image synthesis, enabling visualizations within standard mammographic hanging protocols. We hope this work can serve as a useful guide and facilitate further research on GANs in the medical imaging domain.