Comparing Conditional Diffusion Models for Synthesizing Contrast-Enhanced Breast MRI from Pre-Contrast Images

TL;DR

This paper explores the use of conditional diffusion models to synthesize contrast-enhanced breast MRI images from pre-contrast images, aiming to improve diagnostic workflows while reducing reliance on contrast agents.

Contribution

It introduces and compares 22 diffusion model variants with tumor-aware loss functions and segmentation conditioning for improved MRI synthesis accuracy.

Findings

Subtraction image-based models outperform post-contrast models across evaluation metrics.

Tumor-aware losses and segmentation masks improve lesion fidelity and qualitative image realism.

Synthetic images are rated highly realistic by radiologists and technologists.

Abstract

Dynamic contrast-enhanced (DCE) MRI is essential for breast cancer diagnosis and treatment. However, its reliance on contrast agents introduces safety concerns, contraindications, increased cost, and workflow complexity. To this end, we present pre-contrast conditioned denoising diffusion probabilistic models to synthesize DCE-MRI, introducing, evaluating, and comparing a total of 22 generative model variants in both single-breast and full breast settings. Towards enhancing lesion fidelity, we introduce both tumor-aware loss functions and explicit tumor segmentation mask conditioning. Using a public multicenter dataset and comparing to respective pre-contrast baselines, we observe that subtraction image-based models consistently outperform post-contrast-based models across five complementary evaluation metrics. Apart from assessing the entire image, we also separately evaluate the region of interest, where both tumor-aware losses and segmentation mask inputs improve evaluation metrics. The latter notably enhance qualitative results capturing contrast uptake, albeit assuming access to tumor localization inputs that are not guaranteed to be available in screening settings. A reader study involving 2 radiologists and 4 MRI technologists confirms the high realism of the synthetic images, indicating an emerging clinical potential of generative contrast-enhancement. We share our codebase at https://github.com/sebastibar/conditional-diffusion-breast-MRI.