T-SYNTH: A Knowledge-Based Dataset of Synthetic Breast Images

TL;DR

T-SYNTH is a large-scale, open-source dataset of synthetic breast images generated via physics simulations, designed to enhance medical imaging algorithms by supplementing limited real data for detection tasks.

Contribution

This work introduces T-SYNTH, a novel dataset of synthetic mammography and tomosynthesis images created with physics-based simulations, facilitating improved training of medical imaging models.

Findings

Synthetic images show potential for augmenting real datasets.

Initial results indicate improved detection performance.

Dataset is publicly available for research use.

Abstract

One of the key impediments for developing and assessing robust medical imaging algorithms is limited access to large-scale datasets with suitable annotations. Synthetic data generated with plausible physical and biological constraints may address some of these data limitations. We propose the use of physics simulations to generate synthetic images with pixel-level segmentation annotations, which are notoriously difficult to obtain. Specifically, we apply this approach to breast imaging analysis and release T-SYNTH, a large-scale open-source dataset of paired 2D digital mammography (DM) and 3D digital breast tomosynthesis (DBT) images. Our initial experimental results indicate that T-SYNTH images show promise for augmenting limited real patient datasets for detection tasks in DM and DBT. Our data and code are publicly available at https://github.com/DIDSR/tsynth-release.